The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs all Markdown operations by executing the lark-cli binary. This is standard functionality for this vendor-provided integration.
[PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it ingests untrusted content from remote files.
Ingestion points: Remote Markdown content is brought into the agent's context through the +fetch and +diff shortcuts as described in references/lark-markdown-fetch.md and references/lark-markdown-diff.md.
Boundary markers: The skill does not provide instructions to the agent to use delimiters or to ignore potential instructions embedded within the fetched Markdown content.
Capability inventory: The skill allows the agent to modify Drive content through +create, +overwrite, and +patch commands using the lark-cli tool, which could be abused if malicious content is processed.
Sanitization: There is no evidence of sanitization or content validation for the Markdown data retrieved from the Drive.

lark-markdown