lark-whiteboard

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

• Third-party content exposure detected (medium risk: 0.30). The skill workflow involves reading Lark document contents or fetching whiteboards via lark-cli, which can process external user-submitted content from Lark documents, leading to potential indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill contains instructions to install and execute @larksuite/whiteboard-cli via npm/npx from an external registry, but lacks a verifiable repository locator or publisher provenance in the configuration, making it an unverified runtime external dependency evaluated as high.