test-anti-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to perform static diagnostic analysis on test code provided by the user. It does not execute the code under review.
- [SAFE]: Instructions for using shell-based file readers (such as
sed,cat, orGet-Content) include mandatory safety checks, including path normalization and verification that paths remain within the current workspace boundary. - [SAFE]: The skill refers to other agent skills for specialized tasks, following standard platform modularity without introducing external dependencies or remote code execution risks.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted code for analysis. This is inherent to its primary purpose. Ingestion points: Test files and production code are read during the audit workflow. Boundary markers: None defined for wrapping the ingested code. Capability inventory: Includes shell readers (sed, cat, Get-Content) but no file-write or network operations. Sanitization: Path normalization and workspace boundary checks are enforced.
Audit Metadata