AGENT LAB: SKILLS

startup-business-analyst-market-opportunity

Warn

Audited by Snyk on Feb 15, 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 skill's Step 4 explicitly instructs the agent to use "WebSearch" to find industry reports and public company data and "cite all sources with URLs," which requires fetching and interpreting content from open/public third‑party websites (arbitrary URLs), exposing the agent to untrusted external content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:19 PM