feishu-bitable

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or unauthorized access patterns were detected. The skill provides legitimate integration with Feishu Bitable.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and API schemas from trusted vendor domains, including feishu.cn and larksuite.com.\n- [PROMPT_INJECTION]: The skill was evaluated for indirect prompt injection surfaces (Category 8) due to its data-handling capabilities.\n
  • Ingestion points: Data is ingested into the agent context through the list action in feishu_bitable_app_table_record, which retrieves records from external tables.\n
  • Boundary markers: Not present. The skill does not define specific delimiters to isolate record data from instructions.\n
  • Capability inventory: The skill has extensive capabilities, including record creation, modification, and deletion, as well as table and field management.\n
  • Sanitization: No explicit sanitization or data validation logic for record content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:18 PM