browser-login

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow visits an arbitrary user-supplied login URL using browser tools, exposing the agent to untrusted web page content.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill executes npx -y @claude-flow/cli@latest referencing an unverified external npm package and repository without a permanent digest or official domain provenance, establishing a high-tier unverifiable runtime dependency.