test-guard
Pass
Audited by Gen Agent Trust Hub on Jul 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised of markdown documentation and YAML configuration files. It contains no executable scripts, binary files, or automated commands. Its functionality is limited to providing a set of review rules for an AI agent to apply during code analysis.
- [PROMPT_INJECTION]: The skill is designed to analyze untrusted data, specifically test code and Git diffs, which creates a potential surface for indirect prompt injection. However, the risk is negligible due to the skill's limited capability set.
- Ingestion points: Test files (pytest, Jest, PHPUnit), project documentation, and review requests provided in the agent context (SKILL.md).
- Boundary markers: None explicitly defined; the skill relies on the agent's ability to distinguish between its instructions and the code under review.
- Capability inventory: The skill is restricted to generating text-based review reports. It does not contain instructions to execute subprocesses, perform network requests, or modify the user's environment based on the content being reviewed.
- Sanitization: No sanitization is performed on the input code, but the output is confined to descriptive review comments.
Audit Metadata