propose

Warn

Audited by Snyk on May 12, 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 mandatory Research phase explicitly calls for "Web research (when applicable)" and directs the agent to investigate and use web resources to inform its evaluation and proposals, meaning it will fetch/read untrusted public web content that can materially influence decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 12, 2026, 03:47 AM
Issues
1