gpt-pp-team-protocol-replay
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s footprint is coherent with an offensive account/payment replay toolkit, but that purpose itself is high-risk and disproportionate for an AI skill: it automates CAPTCHA solving, anti-fraud evasion, proxy use, payment/auth replay, and refresh-token capture. Install trust is weak because the named publisher does not match the personal GitHub source, and the skill forwards numerous sensitive credentials into cloned third-party code and external services.
Confidence: 93%Severity: 89%
Audit Metadata