The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local shell script located at ./scripts/get_feishu_token.sh to retrieve and refresh authentication tokens. This is an expected mechanism for session management within the skill's operational context.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external source (Feishu) when fetching file lists, downloading file content, or reading comments, which constitutes a potential injection surface.
Ingestion points: Data entering the agent via API endpoints described in SKILL.md, specifically folder children listings, file downloads, and comment retrieval.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious content within these data streams.
Capability inventory: The skill enables the agent to execute local scripts for authentication and perform comprehensive file operations (create, delete, permissions) via the Feishu API.
Sanitization: The skill does not specify any sanitization, filtering, or validation processes for the data retrieved from the Feishu platform.

feishu-drive