The Agent Skills Directory

[SAFE]: The skill definition is purely descriptive and contains no executable scripts or malicious instructions. It provides a standard interface for interacting with the Feishu (Lark) API for document access control.
[INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface by defining a tool that accepts document tokens and member identifiers which may be derived from untrusted user content. * Ingestion points: The token, type, and member_id parameters in the feishu_perm tool definition (SKILL.md). * Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined. * Capability inventory: The tool can modify document permissions, including granting full_access which allows managing permissions for others (SKILL.md). * Sanitization: No input validation or sanitization logic is specified in the skill definition.

feishu-perm