sprinklr

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

• Third-party content exposure detected (high risk: 0.80). This skill’s SKILL.md instructs the agent to use the Membrane CLI (see "Searching for actions" and "Running actions") to fetch Sprinklr entities like Posts, Conversations, Forum Threads, and Comments—user-generated/untrusted content that the agent will read and that can influence its subsequent actions.