higgsfield-acting
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a guide for prompt engineering in the context of character performance for video generation. It does not include any executable code, scripts, or network operations.
- [COMMAND_EXECUTION]: The document mentions
scripts/build_index.py, but this is referenced as a tool used during the skill's build/verification process, not as a command to be executed by the AI agent at runtime. - [PROMPT_INJECTION]: The skill uses natural instructional language and established acting terminology (e.g., 'Objective', 'Tactic', 'Subtext'). There are no attempts to override system prompts, bypass safety filters, or use adversarial prompt techniques like DAN or 'ignore previous instructions'.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were detected. The skill operates on user-provided character descriptions to generate acting profiles.
Audit Metadata