feishu-sheets

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to extract a spreadsheet_token from the URL and include it verbatim in the tool call JSON, forcing the LLM to handle and output a secret-like token.

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

• Third-party content exposure detected (high risk: 0.80). The skill's tools (e.g., feishu_sheets_read_range and feishu_sheets_list_sheets) explicitly fetch spreadsheet contents from Feishu URLs (https://...feishu.cn/sheets/...), and SKILL.md's "Read a spreadsheet" and related workflows require the agent to read and act on that user-generated third-party sheet data, which could contain instructions that materially influence subsequent actions.