skills/tw93/waza/check/Gen Agent Trust Hub

check

Pass

Audited by Gen Agent Trust Hub on May 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill frequently executes shell commands including git (for diffing, logging, and status) and gh (GitHub CLI for issue/PR management). These operations are the primary function of the tool and occur within the user's local repository context.
  • [REMOTE_CODE_EXECUTION]: The skill includes a run-tests.sh script that auto-detects and runs the project's test suite using standard runners such as npm test, cargo test, and pytest. This execution is used for verifying code integrity during the review process.
  • [PROMPT_INJECTION]: The skill processes untrusted data from repository diffs and GitHub issue/PR comments to automate replies and actions. While this represents a surface for indirect prompt injection, the instructions provide a structured framework for factual analysis, and the risk is considered inherent to the core functionality of a repository maintenance tool.
Audit Metadata
Risk Level
SAFE
Analyzed
May 28, 2026, 05:25 PM
Security Audit — agent-trust-hub — check