master-plan-manager
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): Analysis of the skill instructions revealed no malicious patterns, unauthorized data access, or obfuscation. The skill's behavior matches its stated purpose of managing project documentation safely.
- [Indirect Prompt Injection] (LOW): The skill possesses a data ingestion surface by reading MASTER_PLAN.md. Evidence Chain: 1. Ingestion point: MASTER_PLAN.md. 2. Boundary markers: Absent. 3. Capability inventory: File modification, file copying (cp), and git operations. 4. Sanitization: The skill includes instructions for structural validation and manual duplicate checking. Potential for injection is minimized by the instructional nature of the skill and local scope of operations.
Audit Metadata