digital-humans
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [CREDENTIALS_UNSAFE] (SAFE): The skill includes a specific validation rule (
no-api-keys-hardcoded) designed to identify and block the use of hardcoded API keys for services like HeyGen, Synthesia, and D-ID. No actual credentials are leaked within the skill files. - [PROMPT_INJECTION] (SAFE): The content focuses on domain expertise and technical principles for digital humans. There are no attempts to override agent instructions or bypass safety filters.
- [EXTERNAL_DOWNLOADS] (SAFE): No external packages (npm/pip) or remote scripts are requested or executed. The skill operates entirely within the provided markdown and configuration files.
- [DATA_EXFILTRATION] (SAFE): No code or instructions are present that would access sensitive local files or send data to external servers.
- [COMMAND_EXECUTION] (SAFE): The skill contains no executable code, shell commands, or subprocess calls.
Audit Metadata