gpt2api-openai-gateway
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's behavior is coherent with a reverse-engineered gateway, but that purpose itself entails disproportionate handling of imported ChatGPT tokens/cookies, proxy credentials, and user content through a non-official intermediary. The install path is open-source and documented, which lowers malware confidence, but publisher/source mismatch and credential-heavy proxying keep overall risk medium.
Confidence: 88%Severity: 66%
Audit Metadata