The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources (Lark API via the CLI) that could potentially contain malicious instructions or unexpected content aimed at influencing the agent's behavior.
Ingestion points: Data returned from lark-cli attendance user_tasks query is pulled into the agent's context for processing and explanation generation.
Boundary markers: The instructions do not define specific delimiters (such as XML tags or unique markers) to separate the untrusted API data from the skill's system instructions.
Capability inventory: The skill has the capability to execute shell commands via lark-cli and access file content using the Read tool.
Sanitization: There are no documented sanitization or validation steps for the content retrieved from the attendance records before it is presented to the agent or the user.
[COMMAND_EXECUTION]: The skill relies on the execution of the lark-cli binary to perform its core functions.
The skill specifically invokes lark-cli attendance and lark-cli schema commands.
Parameters like employee_type and user_ids are strictly controlled through hardcoded rules to prevent arbitrary user input from manipulating sensitive fields.

lark-attendance