dalle-chatgpt

Warn

Audited by Socket on Sep 1, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The capability matches image generation, but the implementation is not proportionate: it depends on saved ChatGPT web cookies, an SSH key, and a third-party VPS/proxy path rather than OpenAI's official API. The main risk is credential/session exposure and man-in-the-middle control by the proxy operator, not confirmed malware.

Confidence: 88%Severity: 78%
Audit Metadata
Analyzed At
Sep 1, 2026, 05:59 AM
Package URL
pkg:socket/skills-sh/kekewater%2Fhermes-skills%2Fdalle-chatgpt%2F@67706217cdbc962c3bd3630e8b8e82e79ded56ae657f59cbf178dff4edcf745a