deep-research
Warn
Audited by Socket on Apr 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core purpose is plausible, but the skill relies on a nonstandard MQTT + browser-proxy control chain and an unverified extension requirement that is not clearly official or same-publisher. No direct credential theft is shown, yet the intermediary infrastructure makes the data flow and install trust weaker than a normal Gemini integration.
Confidence: 82%Severity: 74%
Audit Metadata