eu-ai-act-report-oliver-schmidt-prietz
Warn
Audited by Socket on Jul 30, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the main reporting function is coherent and mostly benign, but optional Word export introduces a separate unverified skill dependency and local code execution. No clear credential harvesting or exfiltration is present, yet the transitive trust chain and web-to-execution workflow make the skill higher risk than a normal documentation helper.
Confidence: 84%Severity: 56%
Audit Metadata