skills/juliomrqz/skills/test-audit/Gen Agent Trust Hub

test-audit

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a set of instructions for analyzing code quality and test coverage. It primarily reads local files to provide architectural and testing feedback.
  • [COMMAND_EXECUTION]: The skill mentions executing test commands and mutation testing tools (e.g., Stryker, PIT, mutmut, cargo-mutants). These are standard development tools used for the skill's stated purpose of auditing tests. The instructions require the agent to obtain user consent before running these tools.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads source code and configuration files (package.json, package-lock.json, CI files) to understand the project structure. This is necessary for the audit and does not involve exfiltrating data to external domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data (source code and PR descriptions). While this presents an ingestion surface, the risk is minimal as the skill's output is formatted reports for human review, and it includes logic to verify findings against specifications.
  • [DYNAMIC_EXECUTION]: Step 4 describes running mutation testing tools which modify local code to check test strength. This is a controlled development practice and not an obfuscated or malicious dynamic execution pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 08:43 AM