The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local shell script located at ./scripts/get_feishu_token.sh to manage authentication tokens. This script is used to fetch and refresh the tenant_access_token required for API calls.
[INDIRECT_PROMPT_INJECTION]: The skill processes organizational data retrieved from external Feishu API endpoints, which could theoretically contain instructions intended to influence the agent's behavior.
Ingestion points: Data is ingested through various Feishu API GET requests, including /users, /departments, /groups, and /roles (SKILL.md).
Boundary markers: The documentation does not specify explicit delimiters or "ignore" instructions for the data returned by the API.
Capability inventory: The skill has the capability to execute local scripts (get_feishu_token.sh), perform network operations (GET, POST, PUT, DELETE) against the open.feishu.cn domain, and manage local cache files (.feishu_token_cache.json).
Sanitization: No specific sanitization or validation logic for the API responses is described within the skill instructions.

feishu-contact