gh-pr-writing

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local CLI tools including git, gh (GitHub CLI), and bun to perform repository management tasks. These commands are consistent with the skill's primary function of writing and updating Pull Requests.
  • [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection as it processes data from repository files and command outputs.
  • Ingestion points: Reads .github/pull_request_template.md and git show outputs (SKILL.md).
  • Boundary markers: None present; content from the repository is interpolated without delimiters.
  • Capability inventory: The skill uses subprocess calls for git, bun, and gh (SKILL.md).
  • Sanitization: No sanitization or escaping of external repository content is specified before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 04:46 AM
Security Audit — agent-trust-hub — gh-pr-writing