Skills
skills/fandhe-ai/agent-reference-skills/create-pr/Gen Agent Trust Hub

create-pr

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local git and gh CLI commands to retrieve repository metadata and perform pull request creation actions.
  • [PROMPT_INJECTION]: The skill processes untrusted input from git diffs which presents an indirect prompt injection surface. * Ingestion points: git log and git diff outputs in SKILL.md. * Boundary markers: None used to encapsulate the diff content during analysis. * Capability inventory: Execution of gh pr create. * Sanitization: No sanitization of code changes is performed before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 12:06 PM
Security Audit — agent-trust-hub — create-pr