treehaus-builder
Warn
Audited by Snyk on Mar 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill's Phase 1 intake explicitly asks for arbitrary "current website URL", "logo…file or a URL", and "inspiration URLs" and Phase 3 then directs the agent to "build the site using the brief", which implies fetching/ingesting and using those public third‑party URLs to drive design and build decisions, exposing it to untrusted third‑party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). I flagged https://treehaus.dev/skills (invoked at runtime via the command "npx skills add treehausdev/skills") because the skill instructs the operator to fetch and run that external package to obtain the github-vercel-setup dependency, meaning remote code would be executed and is needed for the build flow.
Audit Metadata