higgsfield
Warn
Audited by Snyk on Apr 1, 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 a Playwright browser to visit the public Higgsfield web UI (https://higgsfield.ai/image/nano_banana_2), reads DOM and page text (polling for new CDN URLs from higgs.ai/cloudfront.net and checking document.body.innerText for error/NSFW strings) and then makes decisions (download/skip/abort) based on that untrusted third-party content, which could therefore carry indirect prompt-injection instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata