website_audit
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md instructs the agent to run "npx lighthouse " on a provided URL and parse the resulting Lighthouse JSON (steps 1–3), which ingests and returns raw data from arbitrary public websites that can be used to drive downstream decisions—exposing the agent to untrusted third-party content.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.70). The skill runs the command "npx lighthouse " at runtime, which will fetch and execute the remote "lighthouse" package from the npm registry (e.g., https://registry.npmjs.org/lighthouse), so it relies on and executes externally fetched code.
Audit Metadata