github-pr-writer

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git and gh CLI commands to gather branch context and automate the pull request workflow. These operations are standard for development tasks and are confined to the repository's local environment.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to its requirement to process commit logs and file diffs which could contain malicious instructions.
  • Ingestion points: Data enters the agent context via git log and git diff as specified in SKILL.md.
  • Boundary markers: There are no explicit instructions to the agent to treat external git data as untrusted text using delimiters.
  • Capability inventory: The skill possesses write capabilities through the gh pr create command.
  • Sanitization: While no programmatic sanitization is defined, the skill mandates a safety checkpoint where the agent must display the drafted PR body for user approval before proceeding with the creation command.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 07:12 AM
Security Audit — agent-trust-hub — github-pr-writer