social-intents

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 instructs the agent to use Membrane to run actions (membrane action run ... --json) against Social Intents to retrieve objects like Chat/Transcript/Message (user-generated social/chat content) whose output the agent is expected to read and act on, so untrusted third-party content could influence behavior.