skills/breezewish/codexpotter/loop/Gen Agent Trust Hub

loop

Pass

Audited by Gen Agent Trust Hub on Jun 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git rev-parse HEAD to identify the current commit for state persistence in project handoff files. This is a routine operation for repository-integrated tools.\n- [EXTERNAL_DOWNLOADS]: Contains a link to the author's official GitHub repository (github.com/breezewish/CodexPotter) for setup instructions if the required subagent is missing. This is a neutral reference to documentation.\n- [PROMPT_INJECTION]: The skill constructs an initial_prompt for subagents by incorporating user requests and conversation context. It uses structured Markdown headers as boundary markers to organize this information, minimizing the risk of accidental instruction confusion.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 7, 2026, 12:42 PM
Security Audit — agent-trust-hub — loop