azure-sentinel
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill exclusively references documentation hosted on 'learn.microsoft.com'. As Microsoft is a trusted organization, these external references do not pose a security risk.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by instructing the agent to fetch web pages. However, the attack surface is constrained to a trusted domain, minimizing the risk of malicious instructions being introduced.
- Ingestion points: The agent is instructed to use tools like
microsoft_docs_fetchto retrieve content from the URLs listed in SKILL.md. - Boundary markers: The skill does not define specific delimiters for the fetched content.
- Capability inventory: The skill contains no scripts, command execution, or file-writing capabilities.
- Sanitization: There is no evidence of sanitization for the fetched content, but reliance on a trusted source provides inherent safety.
Audit Metadata