ship

Warn

Audited by Snyk on Apr 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's Phase 1 spec explicitly requires "Research third-party dependencies" (load /research) and elsewhere says "Web search when needed", which instructs the agent to fetch and interpret public third-party docs/web content as part of spec/implementation decisions, so untrusted external content can influence tool use and next actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 14, 2026, 09:29 AM
Issues
1