harness-audit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository being audited, which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: SKILL.md directs the agent to read .agents/harness-anchor.md and project test suites across the repository.
- Boundary markers: The instructions lack explicit markers or warnings to the agent to ignore instructions embedded within the audited test files.
- Capability inventory: The skill is limited to file reading and report generation; it explicitly prohibits file mutation and does not include network or command execution capabilities.
- Sanitization: No sanitization or content validation is performed on the ingested file data before processing.
Audit Metadata