api-void

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md instructs the agent to run Api Void actions (e.g., "Check URL Reputation", "Get Site Trustworthiness") and to use "membrane request CONNECTION_ID /path/to/endpoint" to proxy arbitrary Api Void API calls, which will retrieve and return data about arbitrary public URLs/domains (untrusted third‑party content) that the agent is expected to read and act on.