multi-angle-set
Warn
Audited by Socket on Oct 4, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core purpose is coherent, but the data flow is not: the skill recommends routing image prompts, references, and possibly API credentials through third-party intermediary domains (`tryallapi.com`, `gptimage2.asia`, `chatgpt-plus.top`) rather than official provider endpoints. The Pillow install is benign and proportionate, but the credential/data forwarding to non-official services makes the overall skill high risk.
Confidence: 92%Severity: 84%
Audit Metadata