startup-validator

Warn

Audited by Snyk on Feb 18, 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 requires performing 10–15+ web searches and instructs using web_fetch to read full articles from public sources (see "Always use at least 10-15 web searches" and "CRITICAL: Use web_fetch to read full articles" in SKILL.md and references/research_templates.md which list public sites like TechCrunch, Crunchbase, Stack Overflow, Product Hunt), so the agent will fetch and interpret untrusted third‑party web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 18, 2026, 12:02 AM