surprise-me

Warn

Audited by Snyk on Feb 17, 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 fallback in Step 3 explicitly instructs the skill to "Search today's news for a fascinating story" and build an artifact from it, which requires fetching and reading public news websites (untrusted third-party content) as part of the workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 01:28 AM