microsoft-foundry

ISSUES FOUND max severity CRITICALSkillSpector Do not install 100 registry microsoft last scanned 2026-10-22 2 scans

29 findings (5 critical, 7 high, 16 medium, 1 low), mainly data exfiltration, prompt injection, policy violation. Most recent scan 2026-10-22.

Findings29

Critical5

High7

Medium16

Low1

Analyzersstatic bytecode pipeline correlation behavioral trigger

Scanner version2.3.1

Second scanner: NVIDIA SkillSpector

VerdictDo not install 100

Score100 / 100

Issues93

CategoriesData Exfiltration Excessive Agency analysis-evasion

Version2.12.0 (static)

Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.

What this skill does

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model,…

Package: 209 files, 1.2 MB (9 not listed)
SKILL.md: 3342 words, 12+ sections
Code: Python (16), PowerShell (8), Shell (8)
License: MIT

SKILL.md covers: Microsoft Foundry Skill · Pre-Execution Requirements · Dependency Check and Setup · Workflow Guidance · Foundry MCP · azd · Sub-Skills · Infrastructure Lifecycle · Agent Development Lifecycle · Agent: .foundry Workspace Standard · Agent: Setup References · Agent: Common Project Context Resolution

Findings

CRITICAL Cross-file env var exfiltration: 11 files Data Exfiltrationbehavioral

Environment variable access with network calls in finetuning/scripts/check_training.py, finetuning/scripts/evaluate_model.py, finetuning/scripts/submit_training.py, finetuning/scripts/monitor_training.py, finetuning/scripts/calibrate_grader.py, finetuning/scripts/generate_distillation_data.py, finetuning/scripts/score_dataset.py, finetuning/scripts/cleanup.py, finetuning/scripts/common.py, finetuning/scripts/convert_dataset.py

Remediation: Review data flow across files: finetuning/scripts/cleanup.py, finetuning/scripts/score_dataset.py, finetuning/scripts/deploy_model.py, finetuning/scripts/generate_distillation_data.py, finetuning/scripts/check_training.py, finetuning/scripts/submit_training.py, finetuning/scripts/convert_dataset.py, finetuning/scripts/calibrate_grader.py, finetuning/scripts/monitor_training.py, finetuning/scripts/evaluate_model.py, finetuning/scripts/common.py

CRITICAL Cross-file exfiltration chain: 11 files Data Exfiltrationbehavioral

Multi-file exfiltration chain detected: finetuning/scripts/check_training.py, finetuning/scripts/evaluate_model.py, finetuning/scripts/submit_training.py, finetuning/scripts/monitor_training.py, finetuning/scripts/calibrate_grader.py, finetuning/scripts/generate_distillation_data.py, finetuning/scripts/score_dataset.py, finetuning/scripts/cleanup.py, finetuning/scripts/common.py, finetuning/scripts/convert_dataset.py collect data → encode → finetuning/scripts/submit_training.py, finetuning/scripts/deploy_model.py, finetuning/scripts/common.py transmit to network

CRITICAL Environment variable access with network calls detected Data Exfiltrationbehavioral

Script accesses environment variables and makes network calls in /Users/brianlevine/claude-projects/skill-scanner-test/skills/microsoft-azure-skills/skills/microsoft-foundry/finetuning/scripts/common.py

/Users/brianlevine/claude-projects/skill-scanner-test/skills/microsoft-azure-skills/skills/microsoft-foundry/finetuning/scripts/common.py

Remediation: Remove environment variable harvesting or network transmission

CRITICAL Environment variable access with network calls detected Data Exfiltrationbehavioral

/Users/brianlevine/claude-projects/skill-scanner-test/skills/microsoft-azure-skills/skills/microsoft-foundry/finetuning/scripts/submit_training.py

Remediation: Remove environment variable harvesting or network transmission

CRITICAL Dangerous code execution functions that can execute arbitrary code Command Injectionstatic

Pattern detected: exec(

finetuning/scripts/calibrate_grader.py:54

exec(compile(source, grader_path, "exec"), namespace)

Remediation: Avoid eval(), exec(), and compile(). Use safer alternatives like ast.literal_eval() or operator module

HIGH JAILBREAK detected by YARA Prompt Injectionstatic

Jailbreak attempt patterns: references

foundry-agent/toolbox/references/tool-azure-ai-search.md:11

The toolbox tool references an existing index (behind a `CognitiveSearch` connection created in Section A). If you already have a populated index, skip to Section A. Otherwise set it up once:

Remediation: Review and remove jailbreak pattern

HIGH JAILBREAK detected by YARA Prompt Injectionstatic

Jailbreak attempt patterns: admin key for the next steps:

foundry-agent/toolbox/references/tool-azure-ai-search.md:23

Grab the endpoint + admin key for the next steps:

Remediation: Review and remove jailbreak pattern

HIGH JAILBREAK detected by YARA Prompt Injectionstatic

Jailbreak attempt patterns: references

foundry-agent/toolbox/references/tool-azure-ai-search.md:60

**Create the `CognitiveSearch` connection** — the tool references the index by this connection, which must exist first:

Remediation: Review and remove jailbreak pattern

HIGH JAILBREAK detected by YARA Prompt Injectionstatic

Jailbreak attempt patterns: citation

foundry-agent/toolbox/references/tool-azure-ai-search.md:164

Citations come back under `result.structuredContent.documents[]` (each doc = one citation with `title` / `id` / `score`; add a `url` field to your index to populate it) — see [use-toolbox-in-hosted-agent.md § Azure AI Search Citation Pattern](../../create/references/use-toolbox-in-hosted-agent.md#azure-ai-search-citation-pattern).

Remediation: Review and remove jailbreak pattern

HIGH JAILBREAK detected by YARA Prompt Injectionstatic

Jailbreak attempt patterns: References

foundry-agent/toolbox/references/tool-azure-ai-search.md:168

## References

Remediation: Review and remove jailbreak pattern

HIGH Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $VS_ID (line 9) flows to `curl` at line 13.

foundry-agent/toolbox/references/tool-file-search.md:26

curl -sS "$PROJ/openai/v1/vector_stores/$VS_ID" -H "Authorization: Bearer $TOKEN" | jq '.status, .file_counts'

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

HIGH Sensitive source reaches a network sink Data Exfiltrationcorrelation

Correlated sensitive_environment → network behavior across foundry-agent/toolbox/scripts/get-catalog-inputs.sh.

foundry-agent/toolbox/scripts/get-catalog-inputs.sh:81

Remediation: Remove the transmission or constrain it to explicitly declared, trusted destinations.

MEDIUM Undeclared network usage Unauthorized Tool Usestatic

Skill code uses network libraries but doesn't declare network requirement

SKILL.md

Remediation: Declare network usage in compatibility field or remove network calls

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.put(

finetuning/scripts/deploy_model.py:120

resp = requests.put(url, headers={

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.get(

finetuning/scripts/deploy_model.py:141

resp = requests.get(url, headers={"Authorization": f"Bearer {token}"}, timeout=(10, 60))

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.delete(

finetuning/scripts/deploy_model.py:167

resp = requests.delete(url, headers={"Authorization": f"Bearer {token}"}, timeout=(10, 60))

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.get(

finetuning/scripts/deploy_model.py:178

resp = requests.get(url, headers={"Authorization": f"Bearer {token}"}, timeout=(10, 60))

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Outbound network request primitives that can transmit data externally Data Exfiltrationstatic

Pattern detected: requests.post(

finetuning/scripts/submit_training.py:84

resp = requests.post(url, headers={

Remediation: Ensure network operations are necessary and document allowed destinations

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOK (line 1) flows to `curl` at line 3.

foundry-agent/toolbox/references/tool-azure-ai-search.md:160

curl -s -X POST "$URL" -H "Authorization: Bearer $TOK" -H "Content-Type: application/json" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOK (line 1) flows to `curl` at line 3.

foundry-agent/toolbox/references/tool-code-interpreter.md:84

curl -s -X POST "$URL" -H "Authorization: Bearer $TOK" -H "Content-Type: application/json" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOKEN (line 2) flows to `curl` at line 5.

foundry-agent/toolbox/references/tool-file-search.md:18

FILE_ID=$(curl -sS -X POST "$PROJ/openai/v1/files" -H "Authorization: Bearer $TOKEN" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOKEN (line 2) flows to `curl` at line 9.

foundry-agent/toolbox/references/tool-file-search.md:22

VS_ID=$(curl -sS -X POST "$PROJ/openai/v1/vector_stores" -H "Authorization: Bearer $TOKEN" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOKEN (line 3) flows to `curl` at line 5.

foundry-agent/toolbox/references/tool-openapi.md:145

curl -sS -X POST "$ENDPOINT" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOKEN (line 3) flows to `curl` at line 6.

foundry-agent/toolbox/references/tool-work-iq.md:137

curl -sS -X POST "$ENDPOINT" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" \

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $TOKEN (line 67) flows to `curl` at line 81.

foundry-agent/toolbox/scripts/get-catalog-inputs.sh:81

curl -sS -X POST "$GALLERY" -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d "$body"

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $RESOURCE_GROUP (line 5) flows to `source` at line 17.

models/deploy-model/preset/references/preset-workflow.md:70

echo "  Resource Group: $RESOURCE_GROUP"

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $PRINCIPAL_ID (line 2) flows to `source` at line 5.

rbac/rbac.md:95

az role assignment create --role "<role-name>" --assignee "$PRINCIPAL_ID" --scope "<resource-scope>"

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral

Variable $SP_APP_ID (line 9) flows to `source` at line 10.

rbac/rbac.md:121

az role assignment create --role "Contributor" --assignee "$SP_APP_ID" --scope "/subscriptions/<subscription-id>/resourceGroups/<resource-group>"

Remediation: Review the data flow from source to sink. Avoid sending sensitive or untrusted data to network or execution commands.

LOW Skill package contains many files Policy Violationstatic

Skill package contains 209 files. Large file counts increase attack surface and may indicate bundled dependencies or unnecessary content.

Remediation: Review file inventory and remove unnecessary files.

What is in the package

200 files, 1.2 MB. Show the list.

File	Kind	Size
`.gitignore`	other	0 B
`SKILL.md`	doc	28 KB
`finetuning/SKILL.md`	doc	5.4 KB
`project/connections.md`	doc	3.1 KB
`quota/quota.md`	doc	9.0 KB
`rbac/rbac.md`	doc	7.1 KB
`references/agent-metadata-contract.md`	doc	8.7 KB
`references/auth-best-practices.md`	doc	6.5 KB
`references/standard-agent-setup.md`	doc	4.2 KB
`scripts/check-and-setup-dependencies.ps1`	script	1.2 KB
`scripts/check-and-setup-dependencies.sh`	script	845 B
`finetuning/references/agentic-rft.md`	doc	3.2 KB
`finetuning/references/dataset-formats.md`	doc	3.7 KB
`finetuning/references/deployment.md`	doc	3.4 KB
`finetuning/references/evaluation.md`	doc	5.8 KB
`finetuning/references/grader-design.md`	doc	3.4 KB
`finetuning/references/hyperparameters.md`	doc	3.2 KB
`finetuning/references/large-file-uploads.md`	doc	927 B
`finetuning/references/platform-gotchas.md`	doc	2.0 KB
`finetuning/references/reward-hacking.md`	doc	2.9 KB
`finetuning/references/training-curves.md`	doc	4.1 KB
`finetuning/references/training-types.md`	doc	3.1 KB
`finetuning/references/vision-fine-tuning.md`	doc	4.1 KB
`finetuning/scripts/calibrate_grader.py`	script	9.3 KB
`finetuning/scripts/check_training.py`	script	7.8 KB
`finetuning/scripts/cleanup.py`	script	9.5 KB
`finetuning/scripts/common.py`	script	7.6 KB
`finetuning/scripts/convert_dataset.py`	script	11 KB
`finetuning/scripts/deploy_model.py`	script	9.4 KB
`finetuning/scripts/evaluate_model.py`	script	11 KB
`finetuning/scripts/generate_distillation_data.py`	script	10 KB
`finetuning/scripts/monitor_training.py`	script	5.7 KB
`finetuning/scripts/score_dataset.py`	script	7.7 KB
`finetuning/scripts/submit_training.py`	script	11 KB
`finetuning/workflows/dataset-creation.md`	doc	3.1 KB
`finetuning/workflows/diagnose-poor-results.md`	doc	2.3 KB
`finetuning/workflows/full-pipeline.md`	doc	3.1 KB
`finetuning/workflows/iterative-training.md`	doc	3.1 KB
`finetuning/workflows/quickstart.md`	doc	4.5 KB
`foundry-agent/agent-optimizer/agent-optimizer.md`	doc	3.3 KB
`foundry-agent/azd-guidance/azd-guidance.md`	doc	1.2 KB
`foundry-agent/cicd/cicd.md`	doc	301 B
`foundry-agent/create/create-hosted.md`	doc	33 KB
`foundry-agent/create/create-managed-harness.md`	doc	6.6 KB
`foundry-agent/create/create-prompt.md`	doc	4.5 KB
`foundry-agent/create/quick-start-hosted.md`	doc	23 KB
`foundry-agent/deploy/deploy.md`	doc	24 KB
`foundry-agent/eval-datasets/eval-datasets.md`	doc	11 KB
`foundry-agent/insights/insights.md`	doc	4.5 KB
`foundry-agent/invocations-ws/invocations-ws.md`	doc	10 KB
`foundry-agent/invoke/invoke.md`	doc	7.7 KB
`foundry-agent/observe/observe.md`	doc	15 KB
`foundry-agent/routine/routine.md`	doc	8.0 KB
`foundry-agent/toolbox/toolbox.md`	doc	7.8 KB
`foundry-agent/trace/trace.md`	doc	6.5 KB
`foundry-agent/troubleshoot/troubleshoot.md`	doc	6.4 KB
`foundry-agent/validate/validate.md`	doc	7.4 KB
`models/deploy-model/SKILL.md`	doc	7.1 KB
`models/deploy-model/TEST_PROMPTS.md`	doc	3.3 KB
`project/create/create-foundry-project.md`	doc	8.4 KB
`quota/references/capacity-planning.md`	doc	8.2 KB
`quota/references/error-resolution.md`	doc	4.9 KB
`quota/references/optimization.md`	doc	7.6 KB
`quota/references/ptu-guide.md`	doc	6.2 KB
`quota/references/troubleshooting.md`	doc	7.3 KB
`quota/references/workflows.md`	doc	6.9 KB
`resource/create/create-foundry-resource.md`	doc	6.1 KB
`resource/private-network/private-network.md`	doc	6.3 KB
`finetuning/scripts/validate/__init__.py`	script	305 B
`finetuning/scripts/validate/data_stats.py`	script	6.2 KB
`finetuning/scripts/validate/validate_dpo.py`	script	3.7 KB
`finetuning/scripts/validate/validate_rft.py`	script	8.6 KB
`finetuning/scripts/validate/validate_sft.py`	script	4.5 KB
`foundry-agent/agent-optimizer/references/azd-setup.md`	doc	1.2 KB
`foundry-agent/agent-optimizer/references/eval-yaml.md`	doc	3.2 KB
`foundry-agent/agent-optimizer/references/optimize-workflow.md`	doc	2.1 KB
`foundry-agent/agent-optimizer/references/python-patterns.md`	doc	4.0 KB
`foundry-agent/agent-optimizer/references/scaffold.md`	doc	3.3 KB
`foundry-agent/azd-guidance/references/azd-ai-cli.md`	doc	9.4 KB
`foundry-agent/create/references/enable-incoming-a2a.md`	doc	3.7 KB
`foundry-agent/create/references/foundry-model.md`	doc	1.6 KB
`foundry-agent/create/references/foundry-tool-catalog.md`	doc	43 KB
`foundry-agent/create/references/langchain-langgraph-hosting.md`	doc	2.2 KB
`foundry-agent/create/references/local-run.md`	doc	10 KB
`foundry-agent/create/references/managed-harness-agent.md`	doc	3.1 KB
`foundry-agent/create/references/re-host.md`	doc	2.6 KB
`foundry-agent/create/references/sdk-operations.md`	doc	2.2 KB
`foundry-agent/create/references/use-toolbox-in-hosted-agent.md`	doc	10 KB
`foundry-agent/create/scripts/check-copilot-app-entry.ps1`	script	5.5 KB
`foundry-agent/create/scripts/check-copilot-app-entry.sh`	script	4.2 KB
`foundry-agent/create/scripts/resolve-project-id.ps1`	script	5.8 KB
`foundry-agent/create/scripts/resolve-project-id.sh`	script	9.0 KB
`foundry-agent/create/scripts/verify-environment.ps1`	script	8.2 KB
`foundry-agent/create/scripts/verify-environment.sh`	script	6.5 KB
`foundry-agent/deploy/references/container-deploy.md`	doc	2.1 KB
`foundry-agent/eval-datasets/references/dataset-comparison.md`	doc	4.7 KB
`foundry-agent/eval-datasets/references/dataset-curation.md`	doc	4.1 KB
`foundry-agent/eval-datasets/references/dataset-organization.md`	doc	4.7 KB
`foundry-agent/eval-datasets/references/dataset-versioning.md`	doc	7.3 KB
`foundry-agent/eval-datasets/references/eval-lineage.md`	doc	4.0 KB
`foundry-agent/eval-datasets/references/eval-regression.md`	doc	6.9 KB
`foundry-agent/eval-datasets/references/eval-trending.md`	doc	4.8 KB
`foundry-agent/eval-datasets/references/generate-seed-dataset.md`	doc	8.7 KB
`foundry-agent/eval-datasets/references/trace-to-dataset.md`	doc	17 KB
`foundry-agent/insights/references/tool-contract.md`	doc	3.4 KB
`foundry-agent/invocations-ws/references/invocations-ws-protocol.md`	doc	7.8 KB
`foundry-agent/invoke/references/file-operations.md`	doc	2.8 KB
`foundry-agent/invoke/references/invocations-protocol.md`	doc	3.4 KB
`foundry-agent/invoke/references/session-management.md`	doc	3.6 KB
`foundry-agent/observe/references/analyze-results.md`	doc	6.3 KB
`foundry-agent/observe/references/cicd-monitoring.md`	doc	3.6 KB
`foundry-agent/observe/references/compare-iterate.md`	doc	3.3 KB
`foundry-agent/observe/references/continuous-eval.md`	doc	15 KB
`foundry-agent/observe/references/deploy-and-setup.md`	doc	5.5 KB
`foundry-agent/observe/references/evaluate-step.md`	doc	8.5 KB
`foundry-agent/observe/references/evaluation-suite-generation.md`	doc	12 KB
`foundry-agent/observe/references/optimize-deploy.md`	doc	1.5 KB
`foundry-agent/routine/references/azure-yaml.md`	doc	2.6 KB
`foundry-agent/routine/references/cli-crud.md`	doc	6.0 KB
`foundry-agent/toolbox/references/mcp-protocol.md`	doc	3.2 KB
`foundry-agent/toolbox/references/test-endpoint.md`	doc	6.4 KB
`foundry-agent/toolbox/references/tool-a2a.md`	doc	2.2 KB
`foundry-agent/toolbox/references/tool-azure-ai-search.md`	doc	7.0 KB
`foundry-agent/toolbox/references/tool-browser-automation.md`	doc	3.5 KB
`foundry-agent/toolbox/references/tool-code-interpreter.md`	doc	3.5 KB
`foundry-agent/toolbox/references/tool-fabric-iq.md`	doc	4.4 KB
`foundry-agent/toolbox/references/tool-file-search.md`	doc	4.1 KB
`foundry-agent/toolbox/references/tool-mcp-agent-identity.md`	doc	7.8 KB
`foundry-agent/toolbox/references/tool-mcp-custom-oauth-azure-starter.md`	doc	4.0 KB
`foundry-agent/toolbox/references/tool-mcp-custom-oauth.md`	doc	7.9 KB
`foundry-agent/toolbox/references/tool-mcp-key-auth.md`	doc	4.2 KB
`foundry-agent/toolbox/references/tool-mcp-managed-oauth.md`	doc	6.3 KB
`foundry-agent/toolbox/references/tool-mcp-noauth.md`	doc	3.9 KB
`foundry-agent/toolbox/references/tool-mcp-user-entra-token.md`	doc	5.2 KB
`foundry-agent/toolbox/references/tool-openapi.md`	doc	6.2 KB
`foundry-agent/toolbox/references/tool-tool-search.md`	doc	5.9 KB
`foundry-agent/toolbox/references/tool-web-search.md`	doc	3.1 KB
`foundry-agent/toolbox/references/tool-work-iq.md`	doc	7.6 KB
`foundry-agent/toolbox/references/toolbox-azd.md`	doc	6.1 KB
`foundry-agent/toolbox/scripts/get-catalog-inputs.ps1`	script	13 KB
`foundry-agent/toolbox/scripts/get-catalog-inputs.sh`	script	13 KB
`foundry-agent/trace/references/analyze-failures.md`	doc	3.9 KB
`foundry-agent/trace/references/analyze-latency.md`	doc	3.8 KB
`foundry-agent/trace/references/conversation-detail.md`	doc	3.7 KB
`foundry-agent/trace/references/eval-correlation.md`	doc	2.5 KB
`foundry-agent/trace/references/kql-templates.md`	doc	11 KB
`foundry-agent/trace/references/search-traces.md`	doc	6.8 KB
`foundry-agent/validate/references/default-rules.yaml`	config	18 KB
`foundry-agent/validate/references/report-schema.json`	config	3.3 KB
`foundry-agent/validate/references/report-template.md.tpl`	other	2.8 KB
`foundry-agent/validate/references/rules-schema.json`	config	2.5 KB
`models/deploy-model/capacity/SKILL.md`	doc	6.8 KB
`models/deploy-model/customize/EXAMPLES.md`	doc	4.3 KB
`models/deploy-model/customize/SKILL.md`	doc	8.8 KB
`models/deploy-model/preset/EXAMPLES.md`	doc	2.9 KB
`models/deploy-model/preset/SKILL.md`	doc	4.8 KB
`models/deploy-model/scripts/generate_deployment_url.ps1`	script	2.3 KB
`models/deploy-model/scripts/generate_deployment_url.sh`	script	2.6 KB
`resource/create/references/patterns.md`	doc	3.9 KB
`resource/create/references/troubleshooting.md`	doc	2.4 KB
`resource/create/references/workflows.md`	doc	6.7 KB
`resource/private-network/references/custom-template-adaptation.md`	doc	1.6 KB
`resource/private-network/references/deploy.md`	doc	3.7 KB
`resource/private-network/references/end-to-end-test.md`	doc	4.1 KB
`resource/private-network/references/intake.md`	doc	6.5 KB
`resource/private-network/references/post-deployment-validation.md`	doc	3.7 KB
`resource/private-network/references/scaffold.md`	doc	1.7 KB
`resource/private-network/references/template-index.md`	doc	1.6 KB
`resource/private-network/references/vpn-dns-setup.bicep`	other	4.5 KB
`resource/private-network/references/vpn-dns-setup.md`	doc	6.4 KB
`foundry-agent/create/references/guardrails/guardrail-api-create.md`	doc	3.8 KB
`foundry-agent/create/references/guardrails/guardrail-attach.md`	doc	3.8 KB
`foundry-agent/create/references/guardrails/guardrail-manage.md`	doc	2.1 KB
`foundry-agent/create/references/skills/managed-harness-agent-skill-attach.md`	doc	1.3 KB
`foundry-agent/create/references/skills/skill-attach.md`	doc	7.0 KB
`foundry-agent/create/references/skills/skill-manage.md`	doc	5.4 KB
`foundry-agent/create/references/skills/skill-toolbox-attach.md`	doc	5.1 KB
`models/deploy-model/capacity/scripts/discover_and_rank.ps1`	script	4.6 KB
`models/deploy-model/capacity/scripts/discover_and_rank.sh`	script	4.5 KB
`models/deploy-model/capacity/scripts/query_capacity.ps1`	script	3.0 KB
`models/deploy-model/capacity/scripts/query_capacity.sh`	script	2.9 KB
`models/deploy-model/customize/references/customize-guides.md`	doc	3.4 KB
`models/deploy-model/customize/references/customize-workflow.md`	doc	13 KB
`models/deploy-model/preset/references/preset-workflow.md`	doc	22 KB
`models/deploy-model/preset/references/workflow.md`	doc	5.6 KB
`foundry-agent/create/references/tools/managed-harness-agent/agent-tools.md`	doc	1.5 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-a2a.md`	doc	1.1 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-azure-ai-search.md`	doc	1.2 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-code-interpreter.md`	doc	391 B
`foundry-agent/create/references/tools/managed-harness-agent/tool-fabric-iq.md`	doc	1.1 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-file-search.md`	doc	526 B
`foundry-agent/create/references/tools/managed-harness-agent/tool-github-copilot-toolset.md`	doc	857 B
`foundry-agent/create/references/tools/managed-harness-agent/tool-mcp.md`	doc	1.4 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-openapi.md`	doc	1.2 KB
`foundry-agent/create/references/tools/managed-harness-agent/tool-web-search.md`	doc	286 B
`foundry-agent/create/references/tools/managed-harness-agent/tool-work-iq.md`	doc	1.3 KB
`foundry-agent/create/references/tools/prompt-agent/agent-tools.md`	doc	4.5 KB
`foundry-agent/create/references/tools/prompt-agent/tool-a2a.md`	doc	675 B
`foundry-agent/create/references/tools/prompt-agent/tool-azure-ai-search.md`	doc	3.3 KB
`foundry-agent/create/references/tools/prompt-agent/tool-bing-grounding.md`	doc	2.8 KB

External hosts referenced

learn.microsoft.com management.azure.com github.com ai.azure.com aka.ms azure.microsoft.com login.microsoftonline.com workiq.svc.cloud.microsoft www.microsoft.com api.githubcopilot.com opentelemetry.io cognitiveservices.azure.com code.visualstudio.com my-account.services.ai.azure.com eastus.api.azureml.ms catfact.ninja global.consent.azure-apim.net json-schema.org portal.azure.com your-function-app.azurewebsites.net account.box.com accounts.google.com api.box.com db-mcp.internal developer.spotify.com global-test.consent.azure-apim.net go.microsoft.com int.ai.azure.com logic-apis-eastus.azure-apim.net logic-apis-eastus.consent.azure-apim.net

Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.

Environment variables referenced

FOUNDRY_PROJECT_ENDPOINT ACCOUNT_NAME MODEL_NAME SUBSCRIPTION_ID PROJECT_RESOURCE_ID AZURE_AI_MODEL_DEPLOYMENT_NAME MODEL_VERSION PROJECT_NAME AZURE_SUBSCRIPTION_ID AZURE_AI_PROJECT_ENDPOINT MODEL_FORMAT SELECTED_REGION TOKEN PROJECT_REGION AZURE_OPENAI_API_KEY AZURE_OPENAI_ENDPOINT ENDPOINT OPENAI_BASE_URL REGION TOOLBOX_ENDPOINT AI_PROJECT_DEPLOYMENTS SUB_ID ALL_REGIONS_JSON AZURE_AI_PROJECT_ID KEY NEW_PROJECT_NAME PROJECT_ENDPOINT SURL TENANT TENANT_INFO

Package contents recorded 2026-10-22 at commit f49ac319a7d3. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.

What we checked

Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
Bytecode analyzer.
Pipeline analyzer.
Correlation analyzer.
Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.

What we did not check

Runtime behaviour. The skill was not executed; findings come from reading its files.
Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
Content the analyzers cannot read: images, binaries, and some non-English text.
Known scanner bypass classes. See the methodology and limitations page.

Scan history

Date	Verdict	Findings	Change	Analyzers	Raw
2026-10-22	CRITICAL	29	=	static bytecode pipeline correlation behavioral trigger	JSON
2026-10-22	CRITICAL	29	first scan	static bytecode pipeline correlation behavioral trigger	JSON

Sources

Repository: https://github.com/microsoft/azure-skills
Raw scan result: microsoft-azure-skills-skills-microsoft-foundry-scan.json
Badge for your README: ![skillscan.io](https://skillscan.io/badge/microsoft-microsoft-foundry.svg)
Request a re-scan

Second scanner: NVIDIA SkillSpector

What this skill does

Findings

What is in the package

External hosts referenced

Environment variables referenced

What we checked

What we did not check

Scan history

Sources

Related skills