implementation
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: The skill processes external 'requested changes' from the agent context (SKILL.md).
- Boundary markers: There are no delimiters or instructions to ignore embedded commands present in the instructions.
- Capability inventory: The skill directs the agent to 'run tests', which involves shell-based execution of code (SKILL.md).
- Sanitization: No input validation or sanitization is defined for the implementation or testing process.
Audit Metadata