harness-audit
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill focuses on technical debt and quality audits within a testing environment. It operates on local files using defined analytical patterns without performing dangerous operations.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for untrusted data via test files. 1. Ingestion points: Local test files and harness anchors. 2. Boundary markers: Absent. 3. Capability inventory: No network or arbitrary command execution tools. 4. Sanitization: Absent. The specific analytical scope limits the impact of potential embedded instructions.
Audit Metadata