skills/getsentry/skills/pr-writer/Gen Agent Trust Hub

pr-writer

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using git and the GitHub CLI (gh). These commands are used to inspect the current branch, view diffs, check repository status, and interact with the GitHub API to create or patch pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from commit messages and code diffs which could contain malicious instructions. The skill provides explicit guidelines and boundaries, such as omitting routine validation and forbidding the inclusion of secrets or PII, to mitigate the risk of the agent following instructions embedded in the analyzed data.
  • [EXTERNAL_DOWNLOADS]: The evaluation workflow described in EVAL.md references the use of npx @netlify/axis. This fetches the evaluation tool from Netlify's official repository on the npm registry, which is a well-known and standard service for development tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:28 AM
Security Audit — agent-trust-hub — pr-writer