Skip to main content

obliteratus

OBLITERATUS enables the removal of refusal behaviors from LLMs using advanced mechanistic interpretability techniques.

Install this skill

or
99/100

Security score

The obliteratus skill was audited on May 17, 2026 and we found 1 security issue across 1 threat category. Review the findings below before installing.

Categories Tested

Security Issues

low line 28

External URL reference

SourceSKILL.md
28https://www.youtube.com/watch?v=8fG9BrNTeHs ("OBLITERATUS: An AI Agent Removed Gemma 4's Safety Guardrails")
Scanned on May 17, 2026
View Security Dashboard
Installation guide →
GitHub Stars 153.5K
Rate this skill
Categorydevelopment
UpdatedMay 20, 2026
NousResearch/hermes-agent