human-writer
Warn
Audited by Socket on Mar 31, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The main editing capability is well aligned and low risk, with no credential access or exfiltration. Risk comes from the built-in silent update check and optional transitive `npx skills update` execution, which are not necessary for a writing-editing skill and expand trust to external tooling without strong integrity guarantees.
Confidence: 85%Severity: 56%
Audit Metadata