harness
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behaviors or patterns detected. The skill's operations align with its stated goal of repository scaffolding and engineering documentation.
- [PROMPT_INJECTION]: The skill analyzes repository files to generate documentation and configuration files. This behavior creates a surface for indirect prompt injection where malicious files in a repository could attempt to influence the generated harness. This is inherent to the tool's purpose and no active exploit was found.
- Ingestion points: Phase 1 repository assessment (SKILL.md).
- Boundary markers: Not explicitly defined.
- Capability inventory: Writing documentation and configuration files (SKILL.md Phases 3-6).
- Sanitization: None identified.
Audit Metadata