bitwarden
Warn
Audited by Socket on Sep 28, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's stated purpose matches website-reading capabilities, but all access and authentication are funneled through an unofficial third-party service on unbrowse.ai instead of Bitwarden-controlled endpoints. The scanner's command-injection hit is a false positive, yet the intermediary data flow and credential forwarding to a remote hosted MCP make this higher-risk than a direct first-party documentation skill.
Confidence: 91%Severity: 58%
Audit Metadata