azure-database-mysql
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill retrieves documentation from learn.microsoft.com and references official resources in the MicrosoftDocs GitHub organization. These are recognized as official and trusted vendor resources.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes remote documentation content, which establishes an indirect prompt injection surface.
- Ingestion points: Documentation is retrieved from learn.microsoft.com using tools like microsoft_docs_fetch as described in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions for the ingested content are defined.
- Capability inventory: The skill mentions the agent's use of the read_file tool for navigating local documentation sections.
- Sanitization: No specific sanitization or filtering of the remote documentation content is implemented within the skill instructions.
- Contextual Assessment: The risk is minimal because the ingestion sources are restricted to trusted, official documentation domains.
Audit Metadata