plan-feature

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a logic-based routing mechanism for engineering planning. It instructs the agent to verify the status of features in docs/features/ROADMAP.md and SPEC.md files before proceeding with planning or redirection to design steps.
  • [COMMAND_EXECUTION]: The skill mentions using the forge CLI to check the fix index and open issues. This is an expected interaction for a development-oriented skill managing project tasks and does not involve arbitrary command execution or shell injection risks.
  • [DATA_EXFILTRATION]: No data exfiltration patterns were identified. The skill's operations are confined to project documentation and standard issue tracking tools within the project environment.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or remote code execution. All referenced skills and resources (e.g., planning-preflight, phase-contract) are relative paths within the skill's own environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 11:08 PM
Security Audit — agent-trust-hub — plan-feature