product-skills
Warn
Audited by Snyk on May 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The competitive-teardown skill explicitly requires collecting and ingesting open/public third‑party signals (websites, app store reviews, job postings, SEO, and social media) — e.g., "Collect data — Use references/data-collection-guide.md to gather raw signals... (website, reviews, job postings, SEO, social)" and concrete examples like App Store and Twitter/X API queries — which the agent is expected to read and use to score competitors and drive action plans, meeting all criteria for untrusted third‑party content influencing behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata