kahneman

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: 1.00). The skill's Teammate 5 ("The Outside Viewer") explicitly instructs the agent to "Use WebSearch and WebFetch to ground this analysis in evidence where possible," meaning the agent will fetch and interpret open/public web content (base rates, articles, statistics) as part of its required workflow, which could expose it to untrusted third-party content that can influence tool actions and 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