paper-to-skill
Warn
Audited by Socket on Apr 12, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The stated purpose is coherent, but the skill has medium risk because it chains untrusted paper/URL content through other unspecified skills and then writes new executable skill packages. The main concerns are transitive trust and indirect prompt injection, not confirmed malware or credential theft.
Confidence: 86%Severity: 61%
Audit Metadata