script-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to perform static analysis of test code. It identifies common testing anti-patterns such as skipped tests, inadequate status code checks, and missing cleanup logic.
- [INDIRECT_PROMPT_INJECTION]: The skill correctly identifies that test files contain untrusted data. It includes defensive instructions for the agent to treat comments or strings within the files as data to be analyzed rather than instructions to be followed.
- Ingestion points: Reads test files and metadata (SKILL.md Workflow Step 1).
- Boundary markers: Explicitly instructs the agent to treat file contents as untrusted data and ignore embedded instructions.
- Capability inventory: The skill is limited to reading files and outputting a report; it contains no file-write, network, or code execution capabilities.
- Sanitization: The agent is instructed to report attempts at command injection found within the data as findings rather than executing them.
- [COMMAND_EXECUTION]: The skill does not perform any shell command execution or runtime compilation. It operates entirely as a reviewer of existing source code.
Audit Metadata