azure-iot-edge

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch and process remote content from learn.microsoft.com using the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools. This creates an indirect prompt injection surface where the agent processes external data as instructions.
  • Ingestion points: Remote documentation content retrieved via the tools specified in the SKILL.md instructions.
  • Boundary markers: The skill does not define specific delimiters or instructions to the agent to treat the fetched content strictly as data.
  • Capability inventory: The skill uses the information to provide troubleshooting, configuration, and architectural guidance.
  • Sanitization: No explicit sanitization or validation of the retrieved Markdown is performed by the skill.
  • [EXTERNAL_DOWNLOADS]: The skill references an external installation guide for the mcp_microsoftdocs tool hosted on the official MicrosoftDocs GitHub repository (github.com/MicrosoftDocs/mcp). This is a legitimate resource from the skill's authoring organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 01:54 PM