w-errors
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process the "current code's failure paths" and external instructions from
AGENTS.md, which creates an attack surface for indirect prompt injection if those files are malicious. - Ingestion points: Analyzes codebase failure paths and the
AGENTS.mddocumentation. - Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed data are provided.
- Capability inventory: The skill directs the agent to "Run the smallest existing check", which involves shell command execution for testing.
- Sanitization: No sanitization or verification steps for the ingested code or documentation are defined.
Audit Metadata