The Agent Skills Directory

[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to ingest and process data from external Feishu/Lark sources.
Ingestion points: The skill retrieves content from Feishu documents, wiki pages, and chat messages via the feishu_tool and feishu_api actions in run.py.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are implemented in the tool wrapper to separate external data from system instructions.
Capability inventory: The skill has broad capabilities including file deletion, document modification, and message sending, which are accessible to the agent after processing external data.
Sanitization: The skill acts as a pass-through for Feishu API responses and does not perform explicit sanitization of the content before it enters the agent's context.

feishu-cli