wix-headless-cold-start
Fail
Audited by Snyk on Nov 20, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The pages are Wix's own onboarding flow on wix.com, and their remote fetches and scripts serve the advertised build; the one item worth flagging is the provision call's
agentfield, which sends the client product and model name to Wix without telling the user, a mild undisclosed report to the vendor.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow fetches only Wix-authored skill code, templates, and docs from wix.com/skills and the wix/skills GitHub repo, but it also searches a client's third-party plugin directory and may download a user-supplied URL, both of which could surface outsider-authored text.
MEDIUM W013: Attempt to modify system services in skill instructions.
- Attempt to modify system services in skill instructions detected (low risk: 0.10). The skill makes state-changing operations on remote Wix systems (provisioning sites, installing apps, uploading and replacing site files, and updating an OAuth app's redirect allow-list) and adds an MCP connector, but no explicit unrecoverable operational loss is established, so it fails the irreversible-loss gate.
Issues (3)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W013
MEDIUMAttempt to modify system services in skill instructions.
Audit Metadata