pull-request

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows standard developer workflow practices by automating the GitHub pull request process. It utilizes the official GitHub CLI (gh) to perform its primary functions, which is consistent with its stated purpose and the vendor's context.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of code changes to generate descriptive metadata for pull requests.
  • Ingestion points: Git diff/changes relative to the main branch as processed in SKILL.md.
  • Boundary markers: Absent; there are no specific markers used to delineate code changes from the instructions.
  • Capability inventory: Execution of gh CLI commands to push code and create pull requests.
  • Sanitization: None; the skill relies on the agent's natural language processing to summarize changes without explicit filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 09:39 AM
Security Audit — agent-trust-hub — pull-request