azure-information-protection
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious behavior, obfuscation, or safety bypass attempts were found. The skill's functionality is purely informational and consistent with its stated purpose.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from 'learn.microsoft.com', which is an official, trusted, and well-known service for technical resources.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from technical documentation pages.
- Ingestion points: Documentation URLs listed in SKILL.md and retrieved via tools.
- Boundary markers (absent): The skill does not define specific delimiters or instructions to ignore instructions embedded in the fetched content.
- Capability inventory: Uses documentation fetching tools (mcp_microsoftdocs or WebFetch).
- Sanitization (absent): No specific filtering or sanitization of the retrieved markdown content is described.
Audit Metadata