newslit

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to use Membrane to query Newslit (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint") to fetch/search Articles and Source content from Newslit's public news feeds, which are untrusted third-party content the agent would read and could influence its subsequent actions.