update-task
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements task management functionality using specialized MCP tools such as
update-todo,update-bug, andadd-task-comment. These operations are limited to the intended platform's API and do not involve arbitrary command execution or file system access. - [PROMPT_INJECTION]: No patterns associated with prompt injection, safety bypasses, or system prompt extraction were detected. The instructions provided are purely operational and focus on maintaining task data integrity.
- [DATA_EXFILTRATION]: The skill does not access sensitive local files (e.g., SSH keys, environment variables) or perform network operations to external domains. All data handling is confined to the One Horizon task management environment.
- [EXTERNAL_DOWNLOADS]: No external packages, remote scripts, or third-party dependencies are referenced or downloaded in the skill content.
Audit Metadata