signals

Warn

Audited by Snyk on Mar 7, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly calls tools that fetch and interpret public, user-generated content—Trustpilot reviews, Instagram/TikTok follower stats, and LinkedIn job listings (see SKILL.md "Data sources" and references/tools-reference.md), and the agent is instructed to read and act on those results to trigger signals and decide next steps, so untrusted third-party content can influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 10:52 AM