liveview-code-review
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious behavior detected. The skill contains architectural guidelines and security checklists for Elixir developers.
- Indirect Prompt Injection (SAFE): The skill processes untrusted user-provided code for review purposes. However, it lacks any dangerous capabilities (e.g., shell access, network requests) that could be leveraged by an attacker. 1. Ingestion points: User-provided Elixir and HEEx source code. 2. Boundary markers: None. 3. Capability inventory: Restricted to text analysis and reasoning. 4. Sanitization: None.
- External References (SAFE): The skill contains relative path links to internal reference documents and related protocol files, which are standard for documentation and pose no security risk.
Audit Metadata