skills/akillness/rtk/pr-triage/Gen Agent Trust Hub

pr-triage

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple commands using the gh (GitHub CLI) utility to fetch repository information, list pull requests, retrieve diffs, and post comments. It also uses pbcopy to copy the generated triage table to the local system clipboard for the user's convenience.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub PR bodies and code diffs) and interpolates them into a subagent prompt for review.
  • Ingestion points: Pull request body content and diff outputs are retrieved using gh pr view and gh pr diff in SKILL.md.
  • Boundary markers: The skill does not use specific delimiters or instructions to prevent the subagent from following instructions embedded within the PR content.
  • Capability inventory: The agent has the ability to post comments back to GitHub via gh pr comment and to copy data to the local clipboard via pbcopy.
  • Sanitization: There is no automated sanitization of the fetched PR content. However, the risk is significantly mitigated by a mandatory validation step using AskUserQuestion before any comments are actually posted to the repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 03:44 AM
Security Audit — agent-trust-hub — pr-triage