foundry-iq
Verdict safe, but 2 findings (1 medium, 1 low), mainly unauthorized tool use. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Foundry IQ knowledge bases. WHEN: make local or Blob documents searchable; create/diagnose KBs; triage unsupported connectors or multi-source KB creation/reconfiguration (even with classic-search terms); connect existing KB to agents (including multi-source KBs); create/reuse a Search service; retrieve from an existing knowledge base with citations; no brand words needed. Read its procedure before query/target questions. NOT: other KB providers, repository-file search, classic Azure AI Search index/query/app work with no Foundry IQ KB or connector request, generic agent creation.
- Package
- 85 files, 1.2 MB
- SKILL.md
- 380 words, 1 sections
- Code
- Python (40)
- License
- MIT
- Compatibility
- Azure
SKILL.md covers: Foundry IQ
Findings
MEDIUM Undeclared network usage Unauthorized Tool Usestatic
Skill code uses network libraries but doesn't declare network requirement
SKILL.md
LOW Script contacts a destination the documentation never mentions Unauthorized Tool Usestatic
Script contacts or configures 'schemas.openxmlformats.org' but the skill documentation never visibly mentions it. Undocumented network destinations can indicate behaviour the manifest and description do not disclose.
helpers/_document_adapters.py:23
What is in the package
85 files, 1.2 MB. Show the list.
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 3.7 KB |
agents/connect-hosted-toolbox.md | doc | 7.8 KB |
agents/connect-hosted.md | doc | 7.8 KB |
agents/connect-prompt-sdk-fallback.md | doc | 7.8 KB |
agents/connect.md | doc | 7.8 KB |
agents/create-missing-agent.md | doc | 7.8 KB |
helpers/_blob_observation.py | script | 4.4 KB |
helpers/_blob_source_read.py | script | 39 KB |
helpers/_bootstrap_io.py | script | 30 KB |
helpers/_cleanup_dependencies.py | script | 28 KB |
helpers/_cleanup_receipts.py | script | 14 KB |
helpers/_common.py | script | 36 KB |
helpers/_document_adapters.py | script | 15 KB |
helpers/_document_limits.py | script | 3.9 KB |
helpers/_embedding.py | script | 7.0 KB |
helpers/_file_inventory.py | script | 24 KB |
helpers/_file_source_config.py | script | 16 KB |
helpers/_indexer_observation.py | script | 7.1 KB |
helpers/_initial_prompt.py | script | 12 KB |
helpers/_private_json.py | script | 2.4 KB |
helpers/_progress.py | script | 12 KB |
helpers/_prompt_read.py | script | 18 KB |
helpers/_search_read.py | script | 6.0 KB |
helpers/_source_readback.py | script | 1.6 KB |
helpers/blob-contracts.md | doc | 7.8 KB |
helpers/blob-cu-contracts.md | doc | 7.8 KB |
helpers/blob_inventory.py | script | 17 KB |
helpers/blob_recheck.py | script | 65 KB |
helpers/blob_source.py | script | 36 KB |
helpers/bootstrap-contracts.md | doc | 7.8 KB |
helpers/bootstrap_azure.py | script | 41 KB |
helpers/cleanup_plan.py | script | 41 KB |
helpers/contracts.md | doc | 7.8 KB |
helpers/cu_ingestion_auth.py | script | 12 KB |
helpers/document-assessment.md | doc | 7.8 KB |
helpers/document_assess.py | script | 14 KB |
helpers/file-upload-recovery.md | doc | 7.8 KB |
helpers/file_cu_canary.py | script | 33 KB |
helpers/file_cu_mi.py | script | 9.6 KB |
helpers/file_ingest.py | script | 15 KB |
helpers/file_source.py | script | 32 KB |
helpers/file_upload.py | script | 54 KB |
helpers/hosted_connect.py | script | 31 KB |
helpers/kb-contracts.md | doc | 7.8 KB |
helpers/knowledge_base_retrieve.py | script | 7.7 KB |
helpers/model-discovery-contracts.md | doc | 7.8 KB |
helpers/model-discovery-scopes.md | doc | 7.8 KB |
helpers/model_discovery.py | script | 24 KB |
helpers/private-artifacts.md | doc | 7.2 KB |
helpers/private_artifacts.py | script | 4.8 KB |
helpers/prompt_cleanup.py | script | 22 KB |
helpers/prompt_connect.py | script | 62 KB |
helpers/requirements-assessment.txt | doc | 103 B |
helpers/retrieval-verification-contracts.md | doc | 7.8 KB |
helpers/retrieval_verify.py | script | 20 KB |
helpers/search-intake-contracts.md | doc | 7.6 KB |
helpers/search_intake.py | script | 18 KB |
helpers/search_reconcile.py | script | 60 KB |
helpers/source_vector.py | script | 33 KB |
helpers/throttle-recovery.md | doc | 5.0 KB |
helpers/vector-contracts.md | doc | 7.8 KB |
knowledge-bases/create.md | doc | 8.1 KB |
knowledge-bases/retrieve.md | doc | 7.8 KB |
knowledge-sources/create-azure-blob.md | doc | 7.8 KB |
knowledge-sources/create-file.md | doc | 7.8 KB |
lifecycle/cleanup.md | doc | 7.8 KB |
references/abstention.md | doc | 1.0 KB |
references/blob-binding-evidence.md | doc | 7.8 KB |
references/blob-indexer-observation.md | doc | 7.7 KB |
references/blob-ingestion-progress.md | doc | 6.5 KB |
references/blob-readiness-recheck.md | doc | 7.8 KB |
references/blob-vector-readiness.md | doc | 2.6 KB |
references/bootstrap-azure.md | doc | 7.8 KB |
references/content-fit.md | doc | 7.8 KB |
references/cu-ingestion.md | doc | 7.8 KB |
references/file-cu-canary.md | doc | 7.8 KB |
references/intent-routing.md | doc | 7.7 KB |
references/owner.md | doc | 2.1 KB |
references/platform-contracts.md | doc | 7.7 KB |
references/platform-interfaces.md | doc | 7.8 KB |
references/resource-intake.md | doc | 7.8 KB |
references/search-substrate.md | doc | 7.8 KB |
references/standard-cu.md | doc | 7.8 KB |
search-services/create.md | doc | 7.8 KB |
troubleshooting/diagnose.md | doc | 8.7 KB |
External hosts referenced
learn.microsoft.com search.azure.com github.com management.azure.com ai.azure.com svc.search.windows.net schemas.openxmlformats.org models.services.ai.azure.com storage.azure.com www.rfc-editor.org account.services.ai.azure.com cu.services.ai.azure.com ecma-international.org example.blob.core.windows.net example.dfs.core.windows.net models.openai.azure.com pypi.org www.itu.int
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
TOOLBOX_ENDPOINT FOUNDRY_PROJECT_ENDPOINT
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.
Sources
- Repository: https://github.com/microsoft/azure-skills
- Raw scan result: microsoft-azure-skills-github-plugins-foundry-iq-skills-skills-foundry-iq-scan.json
- Badge for your README:
 - Request a re-scan