The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides the ability to read content from external Feishu documents and comments through actions like read, list_blocks, and list_comments. This untrusted data is ingested directly into the agent's context.
Ingestion points: The feishu_doc tool in SKILL.md consumes external data via actions: read, list_blocks, get_block, list_comments, get_comment, and list_comment_replies.
Boundary markers: There are no instructions provided in the skill to use delimiters or specific warnings to ignore instructions embedded within the document content.
Capability inventory: The skill includes significant write and modification capabilities across SKILL.md and references/block-types.md, including write (replace all), append, update_block, delete_block, and create_comment.
Sanitization: The instructions do not mention any sanitization, filtering, or validation of the content retrieved from Feishu before it is presented to the agent.

feishu-doc