pr-to-main

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the project's git history to draft pull request descriptions.
  • Ingestion points: The outputs of git log and git diff commands in SKILL.md are used as context for drafting text.
  • Boundary markers: No delimiters or explicit instructions are used to prevent the agent from obeying instructions embedded within commit messages.
  • Capability inventory: The skill has the capability to write data to a remote repository via the gh pr create command.
  • Sanitization: No programmatic sanitization is present, although Step 3 explicitly requires the agent to ask the user to review the draft before submission.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:51 AM
Security Audit — agent-trust-hub — pr-to-main