The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as Lark calendar events, task descriptions, and document metadata, which could contain malicious instructions designed to manipulate the agent's output.
Ingestion points: Event titles, task names, document metadata, and meeting notes retrieved via lark-cli as documented in SKILL.md.
Boundary markers: Absent; the instructions do not define delimiters or provide specific warnings to the AI to ignore embedded instructions in the fetched data.
Capability inventory: The skill has the capability to write data back to Lark Docs (creating/updating documents) and execute shell commands via lark-cli as described in SKILL.md.
Sanitization: Absent; the skill does not implement filtering or sanitization of the retrieved content before it is processed by the AI.
[COMMAND_EXECUTION]: The skill executes shell commands to perform date calculations and interact with the Lark platform via its command-line interface.
Evidence: The skill explicitly instructs the agent to use the date command for time range determination and lark-cli for data retrieval operations in SKILL.md.
[EXTERNAL_DOWNLOADS]: The skill references and instructs the agent to read external configuration and logic files from the official Lark Suite GitHub repository.
Evidence: Links to the larksuite/cli repository on GitHub for shared logic and authentication rules are provided in SKILL.md.

lark-workflow-weekly-report