skills/epicenterhq/epicenter/git/Gen Agent Trust Hub

git

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the GitHub CLI (gh) to list and view issues, verify usernames, and perform merge operations.\n- [COMMAND_EXECUTION]: Includes usage of high-privilege commands such as gh pr merge --admin, which allows for bypassing branch protections if the executing user has administrative rights.\n- [SAFE]: The skill defines a surface for processing untrusted data by fetching the titles, bodies, and comments of GitHub issues and PRs. This ingestion is essential for its primary purpose of linking issues and drafting descriptions, and it is handled via standard tool output without identified exfiltration risks.\n- [SAFE]: Implements proactive measures in SKILL.md and references/pull-request-guidelines.md to ensure the agent does not include AI attribution watermarks (e.g., 'Generated with Claude Code') in the repository content.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:30 AM