performing-authenticated-scan-with-openvas

Warn

Audited by Socket on Mar 15, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS: the skill is internally coherent and uses mostly official Greenbone tooling, so it does not look malicious or like credential harvesting. However, it equips an AI agent to perform authenticated vulnerability scanning with real credentials against target systems, which is inherently high-risk offensive capability; the private-key handling and autonomous scan execution/scheduling raise security concern despite generally legitimate data flows.

Confidence: 91%Severity: 79%
Audit Metadata
Analyzed At
Mar 15, 2026, 09:40 PM
Package URL
pkg:socket/skills-sh/mukul975%2FAnthropic-Cybersecurity-Skills%2Fperforming-authenticated-scan-with-openvas%2F@767ce2e1789be5daa88d984f8177dfe5e4bd6693