vulnhunter-security-scanner
Warn
Audited by Socket on Sep 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is coherent with its stated purpose and routes credentials to official Anthropic/GitHub endpoints in the described paths, so I do not see evidence of malware or credential harvesting. However, it is still a higher-risk skill because it equips an AI agent for security-vulnerability hunting and code-affecting workflows, and it is installed from mutable source with repo-defined dependencies rather than a strongly verified release path.
Confidence: 84%Severity: 72%
Audit Metadata