vibe-review
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requests access to the Bash tool to execute git-related commands (diff, log, show, remote, wc) and pwd. This is essential for understanding the context of code changes, but it presents a potential command injection surface if the agent environment fails to sanitize user-provided arguments such as file paths or git ranges.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because its core function involves reading and processing untrusted source code from files and pull requests. Ingestion points: Source code content is ingested via the Read, Grep, and git diff tools. Boundary markers: The instructions lack explicit delimiters or safety commands to prevent the agent from following instructions embedded within the code comments or strings of the files being reviewed. Capability inventory: The agent possesses filesystem read access and the ability to execute scoped git commands. Sanitization: No automated sanitization of the ingested code content is specified.
Audit Metadata