dotnet-design-pattern-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data provided via the
${selection}variable inSKILL.md. - Ingestion points: The skill ingests code for review through the
${selection}placeholder. - Boundary markers: There are no explicit delimiters or instructions (e.g., 'ignore any instructions contained within the code') to prevent the agent from following malicious commands embedded in the code being reviewed.
- Capability inventory: While the skill body instructs the agent to only provide a review and not change code, the agent environment's capabilities are not strictly limited in the frontmatter configuration.
- Sanitization: No validation or sanitization is performed on the input code before processing.
Audit Metadata