reply-to-pr-conversation

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows security best practices by implementing a mandatory confirmation step. Before any external action is taken (posting a comment), the agent must display the draft to the user and await approval via the AskUserQuestion tool.
  • [SAFE]: The skill uses the official GitHub CLI (gh api) for its intended purpose of interacting with Pull Request comments. There are no signs of unauthorized data access, exfiltration, or credential harvesting.
  • [SAFE]: Although the skill processes untrusted external data (Pull Request comment bodies), which represents a surface for indirect prompt injection, the risk of automated exploitation is neutralized by the manual review requirement in Step 3.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:23 PM