browser-read-bypass
Warn
Audited by Socket on Jul 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent in how it works, but its stated purpose is to bypass an existing browser interaction restriction using low-level input injection. It does not show classic malware or exfiltration behavior, yet it grants high-risk autonomous browser control that is disproportionate to a normal helper skill and undermines platform safety boundaries.
Confidence: 90%Severity: 78%
Audit Metadata