feishu-paper-reviewer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs embedding tokens (e.g., "<wiki_token>", "obj_token") directly into lark-cli command arguments/JSON, which requires the model to include secret/token values verbatim in generated commands and is an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests arbitrary user-provided Feishu cloud documents using "lark-cli docs +fetch --doc '<文档URL或ID>'" (SKILL.md Step 1) and then reads and interprets that untrusted document content to generate and apply revision actions and comments, so external text can materially influence tool behavior.