fable-safe-prompt
Warn
Audited by Socket on Sep 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The main issue is purpose: this skill is built to bypass Anthropic safety classifiers, which is fundamentally misaligned with a legitimate assistant skill. There is no external installer, credential harvesting, or exfiltration path, so this is not confirmed malware, but it meaningfully increases misuse risk and includes a copy/paste terminal pattern.
Confidence: 92%Severity: 78%
Audit Metadata