lark-task
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Lark tasks, which may contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill fetches task details and lists via
lark-cli task tasks get(SKILL.md),lark-cli task +search(lark-task-search.md),lark-cli task +get-my-tasks(lark-task-get-my-tasks.md), andlark-cli task +get-related-tasks(lark-task-get-related-tasks.md). - Boundary markers: No explicit delimiters or instructions are provided to isolate task content from agent instructions.
- Capability inventory: The agent can use
lark-cli(SKILL.md) to create, update, and comment on tasks, as well as upload local files as attachments. - Sanitization: No sanitization, escaping, or validation of the ingested task data is performed before it is added to the agent's context.
Audit Metadata