feishu-bitasks-manager

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads Feishu multi-dimensional table records via API, which can contain outsider-submitted titles, descriptions, and comments without verification, presenting an indirect prompt injection risk.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). The file assets/config.json contains actual, active-looking credentials for a Feishu application (app_id, app_secret, app_token, and table_id). These are high-entropy strings providing functional access to the Feishu API rather than placeholders.