speckle-syntax-graphql

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to POST GraphQL queries to third-party endpoints (e.g., https://app.speckle.systems/graphql and self-hosted https:///graphql in SKILL.md) and to read/interpret responses (pagination cursors, IDs, referencedObject) as part of its workflow, which exposes it to untrusted/user-generated content that can influence subsequent tool use and actions.