feishu-bitable
Fail
Audited by Snyk on Feb 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill requires the AI to create parameter files containing sensitive values (tenant_access_token, appSecret, app_token, etc.) and pass them to scripts, which forces the LLM to handle and potentially emit secret values verbatim in generated files/outputs.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md decision flow and AI usage examples show it parses user-provided Feishu Bitable URLs (parse-bitable-url.js) and calls APIs to fetch/list records and attachments (scripts/record/get.js, media/file-token-to-url.js), so the agent ingests untrusted, user-generated third‑party table content as part of its workflow which can influence subsequent actions.
Audit Metadata