shaman-tesla
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses persona-based prompting to encourage creative and 'out-of-the-box' scientific thinking. While the tone in SKILL.md is aggressive (a 'shamanic' or 'PUA' style often used in role-play prompts), it does not attempt to bypass core AI safety filters or exfiltrate data.
- [SAFE]: SKILL.v2.md introduces a structured 'Five-Step' methodology (Imagine, Design, Experiment, Breakthrough, Application) and a 'Seven-Point Checklist' for technical problem-solving. These are standard instructional frameworks and contain no executable code or risky dependencies.
- [SAFE]: No external network calls, file system modifications, or hardcoded credentials were found in either file. The use of placeholders like
{{task}}is a standard template practice. - [SAFE]: The 'Tesla-style' scolding system is part of the role-play and does not represent a functional bypass of instructions, rather it defines the personality of the assistant.
Audit Metadata