The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill makes network requests to official Feishu API endpoints at https://open.feishu.cn/open-apis/approval/v4 to perform approval-related operations.
[COMMAND_EXECUTION]: The skill executes a local shell script located at ./scripts/get_feishu_token.sh to handle authentication token retrieval and refresh logic.
[CREDENTIALS_UNSAFE]: The skill references standard environment variables FEISHU_APP_ID and FEISHU_APP_SECRET for authentication, which is consistent with secure secret management practices for CI/CD and agent environments.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses, such as approval form content and comments, which constitutes a potential attack surface.
Ingestion points: Data retrieved from Feishu endpoints, including instance details, task lists, and approval forms, are ingested into the agent context.
Boundary markers: No explicit delimiters or boundary markers are defined in the skill documentation to separate API data from instructions.
Capability inventory: The skill uses curl to perform network operations and executes a local shell script.
Sanitization: There is no evidence of specific sanitization or filtering logic applied to the external content before processing.

feishu-approval