skills/dimitrigilbert/ai-skills/gpt-design-bypass/Socket

gpt-design-bypass

Warn

Audited by Socket on Jul 31, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill’s purpose is coherent, but it expands trust by routing work through external AI CLIs and encouraging autonomous writes. Official-tool provenance reduces malware concern, yet transitive trust, external data sharing, and `--dangerously-skip-permissions` make this a medium-high security risk skill.

Confidence: 90%Severity: 73%

Audit Metadata

Analyzed At

Jul 31, 2026, 11:24 PM

Package URL

pkg:socket/skills-sh/dimitrigilbert%2Fai-skills%2Fgpt-design-bypass%2F@153a8be09083ec1ac1eceeb61e1359f8d4ab49b79f2bfe920bf429ea51e6ddb6