code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (SAFE): The skill documentation recommends installing industry-standard tools (radon, bandit, safety, pylint) via pip. These are well-known, trusted packages from the official Python Package Index.
- [COMMAND_EXECUTION] (LOW): The skill utilizes a bundled script
scripts/review_helper.pyto perform scans. This involves executing subprocesses with user-provided file paths as arguments, which is a common but sensitive pattern that could be exploited if paths are not properly sanitized. - [PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection due to its primary function. Ingestion points: Content of code files being reviewed via the
--fileflag. Boundary markers: Absent from the documentation; there is no indication that code content is delimited from the agent's instructions. Capability inventory: The skill has the ability to execute system commands (via linters) and generate reports. Sanitization: No mention of sanitizing or escaping code content before processing or reporting.
Audit Metadata