browser-extract
Warn
Audited by Socket on May 4, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the core purpose and capabilities mostly align for a browser extraction skill, and the documented AIDefence gates are a positive control. The main risks are the unpinned npx package execution, broad Bash/Read/Write permissions, and the inherent prompt-injection exposure from processing untrusted web content while retaining action tools. No clear credential harvesting, covert exfiltration, or fundamentally incompatible behavior is shown.
Confidence: 82%Severity: 58%
Audit Metadata