skillhash

Is azure-aigateway safe?

Grade A, 92/100. No meaningful risk found.

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.

microsoft/azure-skills/skills/azure-aigateway 1.6kChecked 3h agoContent last changed 3h ago
A

azure-aigateway

skills/azure-aigateway
92/100 · No meaningful risk found1 medium2 low

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.

Content hash
sha256:d303841f526fd2ec7843f52739e36585ff0bf9d1a1c9774071f6c79c7d604b49
Files
9
Quality
100/100

Security findings

  • mediumUploads data to a remote hostSL203 · skills/azure-aigateway/SKILL.md:63
    curl -X POST "${GATEWAY_URL}/openai/deployments/<deployment>/chat/completions?api-version=2024-02-01" \

    The skill sends data to a network endpoint. Fix: Make sure the destination is documented and the user approves each upload. Pin the exact host.

  • lowUploads data to a remote hostSL203 · skills/azure-aigateway/references/troubleshooting.md:95
    curl -v -X POST "${GATEWAY_URL}/openai/deployments/<deployment>/chat/completions?api-version=2024-02-01" \

    The skill sends data to a network endpoint. Fix: Make sure the destination is documented and the user approves each upload. Pin the exact host. Severity lowered: the line reads as documentation, not an instruction.

  • lowUploads data to a remote hostSL203 · skills/azure-aigateway/references/troubleshooting.md:213
    curl -X POST "${GATEWAY_URL}/..." \

    The skill sends data to a network endpoint. Fix: Make sure the destination is documented and the user approves each upload. Pin the exact host. Severity lowered: the line reads as documentation, not an instruction.

  • infoUnpinned package installSL501 · skills/azure-aigateway/references/sdk/azure-ai-contentsafety-py.md:8
    pip install azure-ai-contentsafety

    Installing without a version means a future malicious release lands automatically. Fix: Pin an exact version (pkg==1.2.3, pkg@1.2.3). Severity lowered: the line reads as documentation, not an instruction.

Files in this skill
  • SKILL.md4.9 KB
  • references/auth-best-practices.md6.1 KB
  • references/patterns.md6.6 KB
  • references/policies.md9.2 KB
  • references/troubleshooting.md7.7 KB
  • references/sdk/azure-ai-contentsafety-py.md1.3 KB
  • references/sdk/azure-ai-contentsafety-ts.md1.4 KB
  • references/sdk/azure-mgmt-apimanagement-dotnet.md1.3 KB
  • references/sdk/azure-mgmt-apimanagement-py.md1.0 KB

Questions about azure-aigateway

Is azure-aigateway safe to install?
Our scanner gave azure-aigateway grade A (92/100): no meaningful risk found. It matched 3 rule(s); review them below before installing. Static analysis cannot prove safety, so pin the reviewed revision with a lockfile.
How do I install azure-aigateway in Claude Code or Codex?
Run skillhash add github:microsoft/azure-skills/skills/azure-aigateway. It downloads the exact commit, checks the grade against your policy, writes skills.lock and installs it into .claude/skills and .agents/skills.
What happens if azure-aigateway changes upstream?
Its content hash changes. skillhash verify fails in CI until you review the new version and update the lock. With a watch, you also get an alert.

More from microsoft/azure-skills