azure-bot-service

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches technical documentation in Markdown format from Microsoft's official Learn platform (learn.microsoft.com) to provide real-time guidance on Azure AI Bot Service.\n- [COMMAND_EXECUTION]: The skill instructs the agent to suggest the installation of the mcp_microsoftdocs tool from the author's official GitHub repository if it is not present in the execution environment.\n- [PROMPT_INJECTION]: Indirect prompt injection surface exists as the skill processes external documentation content from the web.\n
  • Ingestion points: Documentation fetched from learn.microsoft.com (as defined in SKILL.md).\n
  • Boundary markers: Absent; there are no specific instructions to ignore embedded commands within the fetched content.\n
  • Capability inventory: Reading local skill files and performing network requests to fetch documentation (SKILL.md).\n
  • Sanitization: Absent; the skill relies on the reputation of the external documentation source.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 02:00 AM