skills/op7418/codepilot/feishu-task/Gen Agent Trust Hub

feishu-task

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as prompt injection, obfuscation, or persistence mechanisms were detected in the skill instructions or examples.
  • [DATA_EXPOSURE]: The skill handles identifiers like open_id and task_guid which are required for the Feishu API. It follows best practices by recommending the retrieval of the user's ID (current_user_id) from the secure message context (SenderId).
  • [COMMAND_EXECUTION]: All tools referenced (feishu_task_task, feishu_task_tasklist) are specialized API wrappers for the Feishu service; no arbitrary shell command execution or unauthorized system access was found.
  • [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads or reference third-party scripts/packages.
  • [SAFE]: Indirect prompt injection risk is evaluated as minimal.
  • Ingestion points: User-provided strings for task summary, description, and tasklist name (SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Task/list creation, updating, member management, and deletion (SKILL.md).
  • Sanitization: None mentioned, but the operations are restricted to the user's authenticated Feishu session permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 04:29 AM