The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of various shell commands through the feishu-cli binary, including tools like jq, curl, and python3 for processing Feishu API data. The execution environment is scoped to specific platform capabilities such as authentication, searching, and directory queries.
[DATA_EXFILTRATION]: The skill handles sensitive authentication tokens (User Access Tokens and Tenant Access Tokens) stored in ~/.feishu-cli/token.json. It provides explicit instructions to prevent the exposure of these secrets in user-facing output or command history and includes mechanisms for secure token management and refresh.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data retrieved from Feishu APIs, such as search results from documents and messages. This represents a potential surface for indirect prompt injection where malicious content embedded in documents or messages could influence agent behavior. The skill mitigates this by requiring structured output and providing clear workflows, but relies on the agent's underlying safety guardrails for data sanitization.

feishu-cli-platform