one-create-task
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for interacting with the One Horizon MCP via specific tools (
create-todo,create-initiative,add-task-comment). All tool parameters and usage examples follow standard task management workflows. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided content (task titles and descriptions) and write it to a task management system. While this creates an attack surface where untrusted data could be persisted, it represents the primary intended functionality of the skill and does not bypass any standard security controls.
Audit Metadata