azure-aigateway
Verdict safe, but 1 finding (1 medium), mainly data exfiltration. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
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
Configure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbreak detection, add Azure OpenAI backend, add AI Foundry model, test AI gateway, LLM policies, configure AI backend, token metrics, AI cost control, convert API to MCP, import OpenAPI to gateway.
- Package
- 9 files, 39 KB
- SKILL.md
- 491 words, 12+ sections
- Code
- None. Instructions only.
- License
- MIT
- Compatibility
- Requires Azure CLI (az) for configuration and testing
SKILL.md covers: Azure AI Gateway · When to Use This Skill · Quick Reference · Get Gateway Details · Get gateway URL · List backends (AI models) · Get subscription key · Test AI Endpoint · Common Tasks · Add AI Backend · Discover AI resources · Create backend
Findings
MEDIUM Bash: tainted data flows to dangerous sink Data Exfiltrationbehavioral
Variable $GATEWAY_URL (line 1) flows to `curl` at line 3.
SKILL.md:53
curl -X POST "${GATEWAY_URL}/openai/deployments/<deployment>/chat/completions?api-version=2024-02-01" \What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 4.9 KB |
references/auth-best-practices.md | doc | 6.1 KB |
references/patterns.md | doc | 6.6 KB |
references/policies.md | doc | 9.2 KB |
references/troubleshooting.md | doc | 7.7 KB |
references/sdk/azure-ai-contentsafety-py.md | doc | 1.3 KB |
references/sdk/azure-ai-contentsafety-ts.md | doc | 1.4 KB |
references/sdk/azure-mgmt-apimanagement-dotnet.md | doc | 1.3 KB |
references/sdk/azure-mgmt-apimanagement-py.md | doc | 1.0 KB |
External hosts referenced
learn.microsoft.com cognitiveservices.azure.com aoai-eastus.openai.azure.com aoai-westus.openai.azure.com github.com raw.githubusercontent.com
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
GATEWAY_URL AZURE_FUNCTIONS_ENVIRONMENT AOAI_ID AZURE_CLIENT_ID PRINCIPAL_ID
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 |
|---|---|---|---|---|---|
| SAFE | 1 | = | static bytecode pipeline correlation behavioral trigger | JSON | |
| SAFE | 1 | first scan | static bytecode pipeline correlation behavioral trigger | JSON |
Sources
- Repository: https://github.com/microsoft/azure-skills
- Raw scan result: microsoft-azure-skills-skills-azure-aigateway-scan.json
- Badge for your README:
- Request a re-scan