nano-nets

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to run Membrane actions and proxy arbitrary API calls (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") to fetch Nano Nets data (notes, files, activities) from a third-party SaaS, which the agent is expected to read and could materially influence subsequent actions.