writing-plans

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a procedural guide for generating structured documentation. It outlines a markdown template for implementation plans and recommends organizing them within the docs/plans/ directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an inherent vulnerability surface by processing untrusted user requirements to produce executable commands for verification and task execution.\n
  • Ingestion points: User-provided requirements, existing source code, and project documentation (SKILL.md).\n
  • Boundary markers: None; the instructions do not specify the use of delimiters or warnings to isolate external data within the generated plan.\n
  • Capability inventory: The agent is authorized to write markdown files to the repository and generate commands for use with planning tools (SKILL.md).\n
  • Sanitization: None; the skill does not provide mechanisms for validating or escaping commands derived from user requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 05:12 AM
Security Audit — agent-trust-hub — writing-plans