agent-awareness

Warn

Audited by Snyk on Feb 28, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md Decision Tree explicitly directs use of the web-search-researcher agent for "Researching external information," which implies fetching and reading open/public web content (untrusted third-party sources) that could influence agent decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 10:32 PM