j5ik2o-gh-issue-organizer

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses several command-line tools to perform its tasks, including gh (GitHub CLI) for issue management, rg (ripgrep) for searching code, and git for tracking file history and renames. These are standard tools for the stated purpose of triaging repository issues.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub issue bodies and comments. While this presents an attack surface where a malicious issue could attempt to influence the agent's behavior, the skill mitigates this by requiring explicit user approval for all modifications (like closing or editing issues) and focusing on objective code verification rather than following natural language instructions found within the issues.
  • Ingestion points: Reads issue titles, bodies, and comments via gh issue list and gh issue view (SKILL.md).
  • Boundary markers: Not explicitly defined for external content, though the skill instructions emphasize parsing and verification.
  • Capability inventory: Can modify issues using gh issue close and gh issue edit (SKILL.md).
  • Sanitization: Relies on the agent's internal safety filters and the mandatory user approval step before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:33 PM
Security Audit — agent-trust-hub — j5ik2o-gh-issue-organizer