skills/kangarooking/kangarooking-skills/multi-agent-image/Socket

multi-agent-image

Warn

Audited by Socket on May 3, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the core capability matches an image-generation skill, but the actual network path is inconsistent with the stated provider. The main risk is credential and prompt routing through apimart.ai while the docs frame usage around OpenAI/GPT-Image-2 and an OPENAI_API_KEY, creating a significant third-party interception risk despite otherwise proportionate local behavior.

Confidence: 90%Severity: 76%

Audit Metadata

Analyzed At

May 3, 2026, 02:55 AM

Package URL

pkg:socket/skills-sh/kangarooking%2Fkangarooking-skills%2Fmulti-agent-image%2F@dc82d236338b76063908ae8f4350eb69045a0e77