research-keywords
Warn
Audited by Socket on Apr 27, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's purpose is coherent, and it avoids direct credential harvesting, but it combines untrusted web ingestion with optional Bash execution of unverified local scripts and possible routing through SerpApi. This is better classified as a moderate-risk research skill than malware.
Confidence: 83%Severity: 56%
Audit Metadata