newslit

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md instructs the agent to use the Membrane CLI to query Newslit (which aggregates public news articles) via commands like "membrane action list" and "membrane action run" to retrieve article content, so the agent will ingest untrusted third‑party/public news content that could influence subsequent actions.