test-codebase
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes codebase content including tests, reproduction steps, and documentation, which constitutes a surface for indirect prompt injection where data could be interpreted as instructions.
- Ingestion points: The skill reads existing tests, targeted reproduction steps, and codebase documentation as part of its validation workflow (SKILL.md).
- Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore or isolate instructions found within the codebase being analyzed.
- Capability inventory: The skill possesses capabilities to execute shell commands (for test runs) and modify the local filesystem by writing to
path/findings.md(SKILL.md). - Sanitization: No sanitization, validation, or filtering mechanisms are defined for the content extracted from the codebase before execution or recording.
Audit Metadata