gentle-ai-chained-pr

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed for structural pull request management and follows standard development workflows. No malicious behaviors, obfuscation, or unauthorized access patterns were detected.
  • [COMMAND_EXECUTION]: The skill uses git and gh (GitHub CLI) for branching, pushing code, and managing pull requests. These operations are restricted to the context of the repository being worked on and do not involve unauthorized system access or sensitive file manipulation.
  • [PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection surfaces (Category 8):
  • Ingestion points: Metadata is retrieved from existing pull requests using gh pr view and from SDD (Software Design Document) planning artifacts.
  • Boundary markers: Not explicitly defined, as the ingested data is used for structural planning rather than command generation.
  • Capability inventory: The skill utilizes git (branching, pushing) and gh (PR creation, viewing) within SKILL.md.
  • Sanitization: Ingested data is primarily used for quantitative analysis (e.g., line counts) and structural mapping, reducing the risk of accidental instruction obedience.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 05:54 AM