SPACE-experiment-designer
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to provide expert guidance on A/B testing and generate documentation. It uses standard statistical formulas and clear logical workflows.
- [PROMPT_INJECTION]: The instructions do not contain any attempts to bypass safety filters, override system instructions, or extract system prompts. The language is purely instructional and task-oriented.
- [DATA_EXFILTRATION]: There are no network operations (such as curl, wget, or fetch) or attempts to access sensitive system files. The skill operates entirely within the context of the user's provided experiment data.
- [COMMAND_EXECUTION]: The skill does not attempt to execute shell commands, manage processes, or modify file permissions. It generates static HTML content intended for local viewing.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied experimental goals and metrics to populate an HTML template. While this is a data ingestion surface, the risk is low as the output is a local document and the skill does not have automated capabilities that could be triggered by malicious input within that data. The use of structured templates and specific metrics reduces the surface for successful injection attacks.
Audit Metadata