eigen-delegation
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION] (SAFE): The skill performs network requests to api.eigenexplorer.com and api-holesky.eigenexplorer.com. These are the intended data sources and do not access sensitive local information.
- [CREDENTIALS_UNSAFE] (SAFE): The skill uses placeholders ($EIGEN_API_KEY, 'YOUR_API_KEY') and environment variables for authentication, avoiding hardcoded secrets.
- [PROMPT_INJECTION] (SAFE): Analyzed for Indirect Prompt Injection surface. 1. Ingestion points: scripts/delegation-api.js (API responses). 2. Boundary markers: Absent. 3. Capability inventory: No subprocess calls, file writing, or administrative commands; operations are limited to axios GET requests. 4. Sanitization: Absent, but the risk is negligible due to the restricted capability set.
Audit Metadata