azerbaijan-website-build
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required runtime workflow for this skill scrapes outsider-authored free text from a user-supplied business website URL (public web content) via Apify RAG Web Browser into
scraped/website/, which is then compiled intoBUSINESS_PROFILE.mdand fed into the agent’s LLM context for subsequent phases.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly calls the Gemini image API at https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent to generate logos at runtime (NanoBanana 2) and injects axe-core from https://cdnjs.cloudflare.com/ajax/libs/axe-core/4.9.1/axe.min.js into pages during QA — both are runtime external resources that execute remote code and are required by the workflow.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata