brooks-test
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructions focus on test quality diagnostics and contain no patterns intended to override agent safety or ignore prior instructions.
- [DATA_EXFILTRATION]: No network access or attempts to access sensitive system files (e.g., .ssh, .aws) are present.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external code.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided code files as part of its primary analysis function.
- Ingestion points: Test files and directories shared by the user.
- Boundary markers: None identified.
- Capability inventory: The skill is limited to text analysis and diagnostic reporting; it does not possess file-writing, network, or shell execution capabilities.
- Sanitization: Not explicitly present.
Audit Metadata