feishu-automation

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes curl examples that embed App ID/App Secret and bearer tokens directly in command bodies/headers (and instructs using those credentials), which would require the agent to accept and insert secret values verbatim—an exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill's MCP configuration template will run "npx -y @larksuiteoapi/lark-mcp mcp ..." (i.e. fetching and executing the remote npm package @larksuiteoapi/lark-mcp at runtime), which causes remote code to be retrieved and executed and is required for the skill's operation, so this runtime external dependency is a risk.