remove-ai-marks
Warn
Audited by Socket on Aug 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s footprint is larger than a simple local cleaning helper because all meaningful processing is outsourced to a configurable HTTP service and optional container image, with full file contents and optional bearer credentials sent there. The anti-detection purpose is explicit, and the unpinned service/container trust chain plus content upload path creates material security and misuse risk, though there is no confirmed malware payload in the skill text itself.
Confidence: 87%Severity: 76%
Audit Metadata