feishu-bitable

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs including an app_token directly as a command-line argument (and to extract it from URLs), which requires the LLM to emit the exact token/value verbatim in generated commands or code, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's CLI and SKILL.md (scripts/bitable_ctl.py and SKILL.md) explicitly fetch and parse Feishu Bitable content (via open-apis/bitable endpoints and by accepting Bitable URLs/app_tokens) and returns record/field data that an agent is expected to read and act on (list/get/filter/update records), so untrusted/user-generated third-party content from Feishu can influence subsequent decisions or tool actions.