skills/ychampion/claude-self-learning/self-learning/Socket

self-learning

Warn

Audited by Socket on Mar 24, 2026

1 alert found:

Anomaly

AnomalySKILL.md

LOW

AnomalyLOW

SKILL.md

SUSPICIOUS: the skill’s stated purpose is coherent, but it combines open-ended web research, persistence into agent skill files, and optional public publication. The main risk is indirect prompt injection and transitive trust: untrusted external content can become reusable agent instructions. No clear credential theft, hidden exfiltration, or incompatible capabilities were found.

Confidence: 87%Severity: 66%

Audit Metadata

Analyzed At

Mar 24, 2026, 06:10 AM

Package URL

pkg:socket/skills-sh/ychampion%2Fclaude-self-learning%2Fself-learning%2F@ddd57d64118348555c6ffe896b96ffc5b5bb791a