The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local script at skills/feishu-cli/run.py using Python 3 to perform API operations on Feishu documents and wikis. This is a standard implementation for CLI-based agent skills.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests untrusted data from external Feishu documents via the read_content and list_blocks actions. This data is processed by the agent to fulfill user requests.
Ingestion points: Data enters the context through doc:read_content and doc:list_blocks (SKILL.md).
Boundary markers: None specified in the instructions to separate external document content from system instructions.
Capability inventory: The agent can execute shell commands via bash to interact with the local CLI script.
Sanitization: No explicit sanitization or validation of the ingested document content is described.

feishu-doc