generic-code-reviewer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- Indirect Prompt Injection (LOW): The skill is designed to ingest and process untrusted project files, which serves as a potential vector for indirect prompt injection. Ingestion points: Project files including package.json, source code (.py, .js, .ts), and HTML files. Boundary markers: None; there are no instructions to the agent to distinguish between its own logic and instructions that might be embedded in code comments or strings. Capability inventory: No active scripts, network operations, or shell commands are defined within this skill. Sanitization: None; the input code is processed as raw text without validation or filtering.
Audit Metadata