promptmateio

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md instructs the agent to use the Membrane CLI (e.g., "membrane action list" and "membrane action run") to fetch and read Promptmate.io data such as Prompts and PromptSets—user-generated third-party content that the agent will interpret and that could materially influence subsequent actions.