create-pr-himarket

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands to manage the Pull Request lifecycle, including git status, git diff, git log, git push, and gh pr create. These are standard tools for developer workflows.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting potentially untrusted data from the local repository environment into the agent's context.
  • Ingestion points: Reads local repository metadata and content via git status, git diff --stat, and git log --oneline -5 (SKILL.md).
  • Boundary markers: Absent. The skill does not define clear delimiters for command outputs.
  • Capability inventory: Subprocess calls for git and gh (GitHub CLI) commands (SKILL.md).
  • Sanitization: Absent. The skill does not specify sanitization or validation of the ingested Git data before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 01:20 AM
Security Audit — agent-trust-hub — create-pr-himarket