The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted meeting data which presents a surface for indirect prompt injection.
Ingestion points: The skill reads transcripts, shared documents, and live event streams via minutes +detail, docs +fetch, and vc +meeting-events.
Boundary markers: No explicit delimiters are required in the instructions to isolate external content from agent instructions.
Capability inventory: The agent can perform write operations such as sending meeting messages, reactions, and updating meeting summaries or titles.
Sanitization: No explicit sanitization or filtering of ingested meeting content is mandated before processing.

lark-meeting