The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data such as task summaries, descriptions, and comments that could contain adversarial instructions intended to influence the agent's behavior.
Ingestion points: Data enters the context through tasks.get, tasks.list, +search, and list-related shortcuts.
Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the prompt templates.
Capability inventory: The skill possesses the ability to create and modify tasks, manage members, and upload files using lark-cli.
Sanitization: There is no evidence of explicit sanitization or filtering of the retrieved task content before it is processed by the agent.
[COMMAND_EXECUTION]: The skill relies on the lark-cli binary to perform all operations, which involves executing shell commands with arguments derived from user input and task data.
[EXTERNAL_DOWNLOADS]: The skill's source is identified as github:larksuite/cli, which points to the official Larksuite GitHub organization, a well-known and trusted service provider.

lark-task