eigen-delegation
Warn
Audited by Snyk on Feb 20, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly fetches live, public data from the EigenExplorer API (https://api.eigenexplorer.com) as shown in SKILL.md and scripts/delegation-api.js, ingesting operator/staker metadata and events which are untrusted third‑party content the agent reads and uses to drive delegation queries and decisions, creating a pathway for indirect prompt injection via malicious metadata or event text.
Audit Metadata