feishu-task
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data such as task summaries and descriptions which could contain instructions for the agent.
- Ingestion points: Data is ingested via the 'summary', 'description', and 'profile_content' fields in the feishu_task_task and feishu_task_agent tools.
- Boundary markers: There are no explicit markers or instructions defined to separate these data inputs from the agent's core instructions.
- Capability inventory: The skill has capabilities to create/modify tasks, manage list members, and upload file attachments.
- Sanitization: No input validation or sanitization mechanisms are described for the data processed from task-related fields.
- [NO_CODE]: The skill is composed entirely of markdown instructions (SKILL.md) and does not include any executable scripts, binaries, or configuration files.
Audit Metadata