pr-writer

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local git and gh (GitHub CLI) commands to inspect the repository state and perform pull request operations. These are standard tools used according to their intended purpose.
  • [EXTERNAL_DOWNLOADS]: It references official engineering documentation from develop.sentry.dev. These links point to a well-known service and do not execute remote code.
  • [PROMPT_INJECTION]: There is a surface for indirect prompt injection as the agent reads output from git log and git diff to construct pull request descriptions. Maliciously crafted commit messages or code changes could potentially influence the agent's output.
  • Ingestion points: Output from git log and git diff in SKILL.md.
  • Boundary markers: Uses a defined Markdown structure for the description but lacks explicit instructions to ignore prompts within the ingested data.
  • Capability inventory: Can create and modify pull requests via gh pr create and gh api in SKILL.md.
  • Sanitization: No sanitization is performed on the ingested git data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 12:44 PM
Security Audit — agent-trust-hub — pr-writer