ce-plan

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes command-line interfaces (gh for GitHub and linear for Linear) to create issues from generated plans. These operations are performed as part of the intended project management workflow.
  • [EXTERNAL_DOWNLOADS]: The skill incorporates external research by calling specialized researcher agents that query web documentation and best practices. These sources are used to inform the planning process and are documented as standard informational lookups.
  • [DATA_EXFILTRATION]: While the skill can send data to external platforms (Slack, GitHub, Linear), these actions are tool-mediated, user-initiated, and target well-known, trusted project management services.
  • [PROMPT_INJECTION]: The instructions contain specific formatting and structural rules (e.g., mandatory repo-relative paths) but do not include patterns typical of safety bypasses or malicious overrides. The use of boundary markers for user input effectively segregates untrusted data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 01:48 AM