shannon

Warn

Audited by Snyk on Apr 23, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The Analogist teammate prompt explicitly instructs the agent to "Use WebSearch if needed to find solved problems in the same domain," which directs the skill at runtime to fetch and interpret open/public web content (untrusted third‑party sources) and use those findings to influence analogies and solution decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 23, 2026, 11:52 PM
Issues
1