upviral

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 shows the agent will fetch and act on data from the UpViral API via Membrane (e.g., "membrane action run" and the "Proxy requests" /path/to/endpoint examples), which can return user-generated/untrusted content (comments, leads, referral data) that the agent is expected to read and could influence subsequent actions.