lark-sheets

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs extracting and reusing tokens (file_token, obj_token, wiki_token, <spreadsheet_token> etc.) in CLI/API commands and shows examples where those token values must be embedded in --params/requests, which would require the LLM to handle and emit secret token values verbatim.

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

• Third-party content exposure detected (high risk: 0.70). The skill accepts arbitrary spreadsheet URLs/tokens (including wiki URLs) and its +read/+find/+info/+export shortcuts explicitly fetch and parse cell contents from those cloud documents, meaning the agent will ingest user-generated third‑party content from external docs that could contain instructions influencing subsequent actions.