openclaw-control-center
Warn
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the user to clone a repository from
https://github.com/TianyiDataScience/openclaw-control-center.git. This source is not categorized as a trusted organization, and the contents of the repository are not directly visible in the skill definition. - [COMMAND_EXECUTION]: The installation and setup process involves executing multiple shell commands, including
npm install,npm run build, andnpm run dev:ui. These commands execute third-party code from the downloaded repository on the host machine. - [INDIRECT_PROMPT_INJECTION]: The dashboard is designed to monitor and display data from agent activities, including chat messages and memory logs, which are external data sources.
- Ingestion points: Agent messages (
HallMessage.content) and memory entries (dailyMemory.entries) are ingested through API calls defined inSKILL.md. - Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the provided snippets.
- Capability inventory: The skill possesses write capabilities, such as task approvals (
/api/tasks/{id}/approve) and document modifications (/api/documents/shared), which could be targeted by instructions hidden in monitored data. - Sanitization: There is no evidence of sanitization or strict schema validation for the data displayed in the dashboard interface.
Audit Metadata