crypto-protocol-diagram

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

• Third-party content exposure detected (high risk: 0.75). This skill’s required workflow includes a “Spec Workflow (S1–S5)” path where it ingests full spec text from either a user-provided file path (Read tool) or a user-provided URL (WebFetch), and then extracts parties/message flow/crypto operations from that readable prose—so if the spec comes from an outsider-authored source, that free text is fed into the agent’s LLM context for processing.