code-review

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes Git and GitHub CLI commands (git diff, git log, gh pr view) to retrieve codebase history and pull request details for analysis. These operations are restricted to standard development information gathering.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface (Category 8) by reading repository-controlled data such as commit messages, PR descriptions, and CONVENTIONS.md files and including them in sub-agent prompts.
  • Ingestion points: Data is sourced from the file system and Git command outputs.
  • Boundary markers: There are no explicit delimiters or instructions to the sub-agents to ignore potential malicious directives embedded in the codebase.
  • Capability inventory: The skill can execute shell commands via Git/GitHub CLI and spawn additional autonomous agents.
  • Sanitization: The skill does not perform validation or sanitization on the content extracted from the repository before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 04:22 AM
Security Audit — agent-trust-hub — code-review