copy-interview
Warn
Audited by Snyk on Apr 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: 1.00). The skill explicitly says "If the user provides a page URL or file path, read it first" (Phase 1), so it fetches and interprets arbitrary user‑provided webpages which may be untrusted third‑party content capable of influencing agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata