cspt
Warn
Audited by Socket on Sep 22, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent as a CSPT hunting guide and shows no installer, credential harvesting, or hidden data exfiltration. However, it is a high-risk offensive security skill because it teaches an AI agent to identify and exploit web vulnerabilities, including bypass and attacker-controlled callback techniques.
Confidence: 95%Severity: 78%
Audit Metadata