feishu-im

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill interacts exclusively with the official Feishu Open API (open.feishu.cn), which is a well-known enterprise service. All documented endpoints and authentication methods follow standard Feishu developer guidelines.\n- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it handles user-provided text for messages and group announcements.\n
  • Ingestion points: Content fields for sending messages (Section II) and updating group announcements (Section III.13).\n
  • Boundary markers: The skill prompt does not provide specific delimiters or instructions to ignore embedded commands within user-controlled data.\n
  • Capability inventory: The skill has broad permissions including message sending, group member management, and workspace configuration.\n
  • Sanitization: No explicit validation or escaping of user-provided strings is defined before submission to the Feishu API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 04:55 PM