email-header-injection
Warn
Audited by Socket on Apr 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is internally consistent as an offensive email-attack playbook, but that purpose itself is high risk for an AI agent. No installer or credential-harvesting behavior is present, yet the content meaningfully enables phishing, spoofing, and email exfiltration against external targets.
Confidence: 92%Severity: 88%
Audit Metadata