pnp-engineering-review
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from articles under review, web search results, and external repositories. Ingestion points: Article body, YAML metadata, third-party search results (Step 12), and linked GitHub implementations (Step 11) as defined in
SKILL.md. Boundary markers: Absent; the instructions do not explicitly mandate delimiters or warnings to ignore instructions within the reviewed content. Capability inventory: Performs web searches and fetches remote repository content via tools as described inSKILL.md. Sanitization: None observed for the ingested external content. - [EXTERNAL_DOWNLOADS]: The skill fetches content from external sources to facilitate review tasks. Step 5 retrieves baseline content from Microsoft Learn and GitHub repositories. Step 11 fetches reference implementations from linked repositories for alignment checks. Step 12 uses a web search tool to gather industry perspectives and competitor documentation for comparison.
Audit Metadata