octoparse

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

• Third-party content exposure detected (high risk: 0.70). The skill’s SKILL.md explicitly allows using Membrane’s proxy to call the Octoparse API (see “Proxy requests” / membrane request CONNECTION_ID /path/to/endpoint), which can return scraped content from arbitrary public websites and thus exposes the agent to untrusted third-party, user-generated content that could influence subsequent actions.