skills/eatsteak/skills/pr/Gen Agent Trust Hub

pr

Pass

Audited by Gen Agent Trust Hub on Apr 25, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git and gh command-line tools to identify branches, inspect logs, calculate diffs, and create pull requests. These operations are essential for the skill's stated purpose and follow standard development practices.\n- [DATA_EXFILTRATION]: There is no evidence of data exfiltration. The skill reads repository information and sends it only to the user's configured GitHub instance via the official CLI tool. No external or unauthorized network operations are performed.\n- [PROMPT_INJECTION]: The instructions do not contain any patterns attempting to override system behavior, bypass safety guidelines, or extract sensitive instructions. The logic is focused on task execution within the repository scope.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 25, 2026, 09:33 AM