remove-ai-marks
Warn
Audited by Socket on Sep 10, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill’s functionality matches its stated purpose, but its architecture is a thin client that uploads full file contents and optionally forwards an API key to a configurable HTTP service. That makes data-flow risk material, especially if operators point WATERMARKS_SERVICE_URL at a remote host. No confirmed malware, obfuscation, or real command-injection behavior is evident from the skill text alone.
Confidence: 87%Severity: 62%
Audit Metadata