skills/starchild-ai-agent/official-skills/skill-manager/Socket

skill-manager

Warn

Audited by Socket on Aug 28, 2026

1 alert found:

Security

SecuritySKILL.md

MEDIUM

SecurityMEDIUM

SKILL.md

SUSPICIOUS: the skill’s purpose generally matches its actions, but it materially expands agent trust by auto-installing third-party skills and forwarding OIDC-backed publish/delete requests to a less-verifiable gateway. The biggest risk is transitive installation of external skills with default auto-install, not confirmed malware.

Confidence: 89%Severity: 72%

Audit Metadata

Analyzed At

Aug 28, 2026, 02:59 AM

Package URL

pkg:socket/skills-sh/starchild-ai-agent%2Fofficial-skills%2Fskill-manager%2F@a03e8e7ed719430f273f3a3af278c1541ece75b3cdc5f43233714c69d7f34456