adding-tests
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill encourages the agent to retrieve reproduction steps and issue details from external GitHub issues using the
ghCLI. - Ingestion point: GitHub issue descriptions and comments (external, untrusted data) referenced in
branches/bug-fix.md. - Capability inventory: The skill's primary purpose is to assist in writing and potentially executing code and tests, which involves file system writes and process execution.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the retrieved issue text.
- Sanitization: There is no mention of sanitizing or validating the content retrieved from the external issue tracker before the agent processes it for code generation.
Audit Metadata