gemini-md-improver
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill reads and evaluates local documentation files which could contain untrusted data, representing an indirect prompt injection surface. Evidence chain: 1. Ingestion points:
SKILL.md(via file discovery). 2. Boundary markers: Absent. 3. Capability inventory: Uses shell commands for discovery and theEdittool for updates. 4. Sanitization: Absent. This risk is mitigated by the explicit requirement for human review and approval before any modifications are applied in Phase 4 and 5.
Audit Metadata