skills/hmbown/codewhale/feishu/Gen Agent Trust Hub

feishu

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill explicitly instructs against hardcoding app secrets or tokens, mandating the use of environment variables (e.g., FEISHU_APP_ID, FEISHU_APP_SECRET) for credential management.
  • [EXTERNAL_DOWNLOADS]: References official API domains for Feishu (open.feishu.cn) and Lark (open.larksuite.com). These are well-known services used for their intended integration purpose.
  • [COMMAND_EXECUTION]: Includes instructions for using platform-specific CLI tools (deepseek mcp) to manage and validate MCP servers. These are standard operations for the intended development workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill features capabilities to read from external sources such as Docs, Sheets, and Bitables.
  • Ingestion points: Reads content from Feishu/Lark Docs, Sheets, Wiki, and Bitables (SKILL.md).
  • Boundary markers: None explicitly defined for isolating external data content.
  • Capability inventory: Includes the ability to send messages and modify document state across Feishu/Lark APIs (SKILL.md).
  • Sanitization: Not explicitly mentioned; however, the skill requires user confirmation before performing write operations or sending visible messages.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 08:12 AM
Security Audit — agent-trust-hub — feishu