skills/cloudflare/cloudflare-docs/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to read existing pull request descriptions using the gh pr view command. This represents a security consideration where untrusted data (the PR body) is brought into the agent's context. However, the skill explicitly instructs the agent to perform minimal edits and requires all new pull requests to be created in 'draft' mode, ensuring a human operator remains in the loop to review changes before they are finalized.
  • Command Line Interaction: The skill utilizes the gh and git command-line interfaces to perform repository management tasks. While the execution of shell commands is a powerful capability, the actions are restricted to standard documentation workflows (viewing diffs, editing titles, and managing PR status) within a specific repository context. The instructions include fallback mechanisms for manual execution, which helps maintain transparency and user control.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 11:53 AM