code-review
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes external source code which could contain malicious instructions designed to influence the agent's review. 1. Ingestion points: File content is ingested via the Read, Grep, and Glob tools for analysis. 2. Boundary markers: The instructions do not define delimiters or specify that comments within code should be treated as untrusted data. 3. Capability inventory: The agent has access to the Bash tool for test execution and file system tools. 4. Sanitization: No input sanitization or filtering is applied to the ingested code before processing.
- [COMMAND_EXECUTION]: The skill requires the ability to execute shell commands to verify code correctness. Evidence: The metadata allows the Bash tool, and the instructions specifically mandate running pytest and reporting the output summary.
- [NO_CODE]: No external scripts or executable files are shipped with this skill; it consists entirely of configuration and instructions in the SKILL.md file.
Audit Metadata