writing-plans

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or unauthorized data access patterns were identified.
  • [SAFE]: The skill uses established planning patterns (TDD, granular tasks) and directs agents to use other sub-skills like 'superjawn:executing-plans' and 'superpowers:subagent-driven-development'. These tools are part of the author's intended workflow and do not represent a security risk in this context.
  • [SAFE]: The skill processes external specification files to generate its output. While this creates a surface for indirect instructions, the risk is minimized by the skill's focus on generating descriptive markdown plans and the inclusion of a secondary review stage (plan-document-reviewer-prompt.md). Ingestion point: SKILL.md and plan-document-reviewer-prompt.md; Boundary markers: None; Capability inventory: Markdown generation and tool handoff; Sanitization: Handled by reviewer sub-agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 07:15 PM
Security Audit — agent-trust-hub — writing-plans