split-task-flow
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional, providing a framework for breaking down complex goals into smaller, manageable sub-tasks for an AI agent.
- [SAFE]: The process involves writing to internal agent directories (
.agents/temp/goals/) and updating project-specific files (plans/INDEX.md), which is standard operational behavior for this type of workflow tool. - [SAFE]: No indicators of prompt injection, data exfiltration, or malicious persistence mechanisms were found.
- [SAFE]: The frontmatter explicitly includes
disable-model-invocation: true, which restricts the skill's capabilities and enhances security by preventing unauthorized model calls.
Audit Metadata