obliteratus-abliteration
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's capabilities mostly match its stated purpose, but the installation trust story is not internally consistent: it directs users to a PyPI package that does not match the cited upstream publisher, while the apparent real source is a separate GitHub repo. That mismatch, combined with executable install steps and default telemetry disclosure gaps, makes this a high supply-chain risk skill rather than clearly malicious content.
Confidence: 94%Severity: 88%
Audit Metadata