writing-plans

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill correctly uses platform-specific tools for task management and user interaction.
  • [NO_CODE]: The skill consists of instructional prompts and templates rather than executable script files.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided specifications to generate plans. This represents an ingestion point for untrusted data.
  • Ingestion points: User-provided software specifications or requirements in SKILL.md.
  • Boundary markers: None explicitly defined to isolate untrusted input.
  • Capability inventory: The skill utilizes task management tools (TaskCreate, TaskList, TaskUpdate), file system writes (saving plans), and the ability to invoke other skills (superpowers-extended-cc:subagent-driven-development).
  • Sanitization: Employs a structured template and a 'Self-Review' checklist to ensure alignment with the specification and prevent placeholders.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 10:10 PM