one-create-task

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a strictly defined workflow for task and initiative management using internal tools such as create-todo, create-initiative, and add-task-comment.
  • [SAFE]: No external network communication, data exfiltration patterns, or hardcoded credentials were detected.
  • [SAFE]: The skill does not include executable code or scripts, relying entirely on natural language instructions for the AI agent.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied data (titles and descriptions) which are passed to task creation tools. This is a standard functional surface.
  • Ingestion points: User-provided text for task titles and descriptions processed via SKILL.md instructions.
  • Boundary markers: Absent in the instruction templates.
  • Capability inventory: create-todo, create-initiative, add-task-comment.
  • Sanitization: Sanitization is handled by the underlying tool implementation in the One Horizon environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 07:47 AM
Security Audit — agent-trust-hub — one-create-task