configurator
Warn
Audited by Snyk on Sep 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to query public RPC endpoints using
curlandWebFetchto fetch blockchain state like block numbers, which exposes the agent to untrusted HTTP response bodies from external servers.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata