plan-retrospective
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-controlled data from project files which could contain hidden instructions (Indirect Prompt Injection). * Ingestion points: plans//prd.md, plans//tasks.md, and plans//decisions.md. * Boundary markers: Absent. * Capability inventory: Reading local files, writing retro.md, and moving project directories. * Sanitization: Absent.
- [COMMAND_EXECUTION]: The skill requests directory move (mv) operations to relocate project folders to plans/archive/. This is a core functionality of the skill and is gated by mandatory user confirmation.
Audit Metadata