one-update-task
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed for direct task management within the One Horizon ecosystem. It uses specific Model Context Protocol (MCP) tools (e.g.,
update-todo,patch-document,add-task-comment) to perform legitimate operations such as changing task status or adding comments. - [SAFE]: There are no indicators of prompt injection, obfuscation, or persistence mechanisms. The instructions focus on best practices for data integrity, such as resolving IDs before updates and providing explanatory comments for status changes.
- [SAFE]: No external network requests to untrusted domains or remote code execution patterns were found. All mentioned tools are part of the required One Horizon MCP infrastructure.
- [SAFE]: The skill processes task data which is a potential surface for indirect prompt injection; however, its specialized and narrow focus on task updates significantly limits exploitable capability chains.
Audit Metadata