bitquery

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md instructs the agent to run Bitquery GraphQL queries via the Membrane CLI (e.g., "GraphQL Query" and examples using membrane action run) and to read the returned blockchain data (public, user-generated/untrusted), which the agent is expected to interpret and could materially influence subsequent actions.