atlan-fact-verification-gate

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md step 4) and the checklist require resolving SDK evidence from "remote source/docs" and recording provenance tags like "[remote-source]" or "[remote-doc]", which means the agent will fetch and read third-party remote documentation that can influence verification decisions and subsequent actions.