microsoft-docs

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill retrieves content from external technical documentation sites to answer user queries. Ingestion points: Data enters the context via search results from search and fetch tools defined in SKILL.md. Boundary markers: No specific delimiters or 'ignore' instructions are defined to separate external search results from core instructions. Capability inventory: The skill's capabilities are limited to documentation search, metadata retrieval, and code sample fetching. Sanitization: The skill relies on official servers to process content from authoritative domains.
  • Verified Documentation Sources: The skill is configured to interact with authoritative domains such as learn.microsoft.com, code.visualstudio.com, and GitHub. These are recognized as safe environments for technical content.
  • Informational CLI Guidance: Guidance on updating local development tools is provided for user reference and does not involve automated or silent command execution by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 06:53 AM
Security Audit — agent-trust-hub — microsoft-docs