writing-plans
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a formatting template for software implementation plans and does not contain malicious code or instructions.
- [PROMPT_INJECTION]: The skill defines a multi-step workflow where its output influences subsequent agent actions (Category 8b). 1. Ingestion points: User-provided feature requirements and task descriptions. 2. Boundary markers: Absent from the plan template. 3. Capability inventory: Templates development commands (pytest, git) and triggers specialized agent 'superpowers' (executing-plans, sub-agent-driven-development). 4. Sanitization: Absent. This surface is inherent to the skill's intended purpose as a coordination tool for multi-step tasks and is considered safe given the trusted source and functionality.
Audit Metadata