bilibili
Warn
Audited by Socket on Jul 9, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is coherent with Bilibili article management, but it relies on high-value browser session cookies captured through a third-party connector flow instead of an official scoped auth model, and it enables real public posting/deletion actions. No strong malware or supply-chain indicators are present, but the credential scope and account-impacting actions make it medium-high risk.
Confidence: 84%Severity: 62%
Audit Metadata