cometchat-native-features

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 integration to read and act on untrusted, user-generated message content (e.g., SmartReplyChips reading incoming message metadata at @injected.extensions.smart-reply in §5d) and documents features that render user-provided URLs and collaborative docs/whiteboards (link previews, collaborative document/whiteboard in §2 and §5), so third-party content can be ingested and influence UI/actions.