prompt-library

Warn

Audited by Snyk on Feb 16, 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 includes agent templates that list the "WebSearch" tool and explicitly call for legal/medical/market research and citing external documentation (e.g., legal-assistant, medical-writer, support-assistant, marketing-strategist), which clearly requires fetching and interpreting public third-party web content that may be untrusted or user-generated.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:25 PM