higgsfield
Warn
Audited by Snyk on Apr 9, 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 automates and reads the public Higgsfield site (higgsfield.ai) — using read_page, javascript_tool/DOM queries, screenshots and extracted result/error text/URLs — and uses that page content to decide navigation, model selection, generation control, and error handling, so untrusted third‑party site content can materially influence agent actions and enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata