self-learning
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is broadly aligned with its stated research-and-skill-generation purpose and uses no external installers or credentials, but it has a meaningful indirect prompt-injection risk because it ingests untrusted web content and turns it into persistent skill files without strong sanitization or instruction-isolation rules.
Confidence: 90%Severity: 56%
Audit Metadata