looper-pr-takeover

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and git to interact with pull requests. These are standard development tools and are used here for their intended purpose of PR management.
  • [EXTERNAL_DOWNLOADS]: The skill mentions fetching extended guidelines from a GitHub repository (https://raw.githubusercontent.com/nexu-io/looper/main/skills/looper-looper-looper-pr-takeover/references/github-commands.md). Per safety guidelines, this is documented neutrally as it targets a well-known service (GitHub).
  • [REMOTE_CODE_EXECUTION]: The skill mentions an optional 'Mode B' using the looper daemon. While this involves a third-party tool, the skill provides a link to its official source and instructs the agent to only use it if already installed and explicitly requested by the user.
  • [PRIVILEGE_ESCALATION]: The skill explicitly forbids using --admin to bypass required checks during merging and prohibits force-pushing, which protects against common repository privilege abuses.
  • [SAFE]: The skill includes extensive safety rails, such as stopping and asking for human intervention when blockers occur or when multiple fix attempts fail.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 12:50 PM
Security Audit — agent-trust-hub — looper-pr-takeover