microsoft-code-reference
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions to bypass safety filters or override system prompts were detected.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or access to sensitive local file paths were found.
- [Indirect Prompt Injection] (LOW): The skill possesses an attack surface for indirect prompt injection as it fetches external data from Microsoft documentation URLs. Ingestion points: External URLs fetched via microsoft_docs_fetch. Boundary markers: None explicitly defined in the instruction file. Capability inventory: Searching and fetching documentation content. Sanitization: Not explicitly documented in the provided markdown file.
Audit Metadata