trust-calibrator
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill consists entirely of natural language instructions and structural templates for a psychological trust-building framework.
- [PROMPT_INJECTION]: While the skill adopts a persona ('Social Psychologist'), it does not contain instructions to ignore system prompts, bypass safety filters, or extract sensitive information.
- [EXTERNAL_DOWNLOADS]: No external packages, scripts, or remote resources are downloaded or executed.
- [DATA_EXFILTRATION]: There are no network operations, API calls, or file system access patterns that could lead to data exfiltration.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic code execution patterns are present.
Audit Metadata