The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the lark-cli binary to perform administrative and lookup tasks against the Lark API. It passes user-provided queries and IDs as command-line arguments to the tool. This is a primary function of the skill for searching and retrieving employee data.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes data from external API responses (Lark directory search results) which are controlled by third parties (other employees in the organization).
Ingestion points: Employee data (names, emails, profile fields) retrieved by lark-cli contact +search-user and lark-cli contact +get-user are fed into the agent's context.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the retrieved employee profiles.
Capability inventory: The agent has the ability to execute further shell commands via lark-cli and read other skill documentation.
Sanitization: There is no evidence of sanitization or filtering of the retrieved employee metadata before it is presented to the agent.

lark-contact