agent-browser
Warn
Audited by Socket on Oct 5, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
The skill is internally coherent: it documents direct use of Oxylabs' browser endpoint with standard CDP libraries and does not show obvious credential exfiltration, hidden installs, or malicious payloads. Risk comes from its intended capability set—autonomous anti-detection web automation, persistent identities, and operation against protected targets—so it is better classified as suspicious/high-risk tooling rather than malware.
Confidence: 89%Severity: 58%
Audit Metadata