browser-extract

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

• Third-party content exposure detected (low risk: 0.10). The agent actively fetches arbitrary web pages via browser tools, ingesting outsider-authored web 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 to fetch and run remote package content, constituting an unverifiable runtime external dependency from an unofficial source with high risk.