vibe-code-leaf-finder
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted codebase files to perform its audit, creating a potential surface for indirect instructions within comments or strings to influence the report.
- Ingestion points: Scans all files in the target scope and git history via instructions in SKILL.md.
- Boundary markers: Absent; it reads file content directly without delimiters to ignore embedded instructions.
- Capability inventory: Employs ripgrep, git log, and a dedicated Write tool for report generation.
- Sanitization: Does not explicitly sanitize file contents before inclusion in the report generation process.
Audit Metadata