skills/deevus/tea-skills/review-pull/Gen Agent Trust Hub

review-pull

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to use the tea CLI to checkout, review, and merge pull requests. These are standard operations for development-oriented agents.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to read pull request diffs, patches, and comments from external repositories. 1. Ingestion points: Reading pull request data via tea pulls (SKILL.md). 2. Boundary markers: No explicit instruction-ignoring delimiters are provided. 3. Capability inventory: Commands to approve, merge, and edit pull request reviewers (SKILL.md). 4. Sanitization: No sanitization of the pull request content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:18 AM
Security Audit — agent-trust-hub — review-pull