proxy-tool-bootstrap

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches proxy lists from ProxyScrape public API where anyone can submit proxy nodes, exposing the agent to untrusted community-sourced entries.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching public proxy lists from api.proxyscrape.com and geolocation data from ip-api.com at runtime to govern proxy routing behavior, presenting weak/unknown third-party operational dependencies.