relentless-quality-assurance-and-fixes
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill body contains logic intended to override or ignore the instructions and safety constraints of a related skill ("relentless-quality-assurance"). Specifically, it explicitly commands the agent to disregard that skill's 'no-fix' policy.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external software code and then perform modifications, which creates a risk for indirect prompt injection if the analyzed code contains malicious instructions.
- Ingestion points: The skill reads external software and code files to identify issues (SKILL.md).
- Boundary markers: Absent. There are no instructions or delimiters to ensure the agent treats the analyzed code strictly as data rather than instructions.
- Capability inventory: The skill allows the agent to modify files ("fix the bugs we find") across the project (SKILL.md).
- Sanitization: Absent. There is no mention of sanitizing or validating the contents of the software being fixed.
Audit Metadata