perf-theory-gatherer
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill instructions focus on analyzing local repository data (git history and code paths) without performing network operations, credential access, or arbitrary code execution.
- [PROMPT_INJECTION]: The skill has a potential ingestion surface for indirect prompt injection as it processes git logs and file contents. Evidence Chain: 1. Ingestion points: Git history and file paths (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: No scripts or external tools defined in the skill content. 4. Sanitization: Absent.
Audit Metadata