pt-maintaining-access
Warn
Audited by Socket on Apr 3, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent as a penetration-testing persistence guide, but it grants an AI agent offensive security capabilities with real-world impact. Lack of external installs or credential routing keeps supply-chain and exfiltration risk low, yet the persistence and lateral-movement focus makes the overall skill high risk and inappropriate outside tightly controlled authorized use.
Confidence: 89%Severity: 76%
Audit Metadata