writing-plans
Warn
Audited by Socket on May 6, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The core planning behavior is coherent and mostly local, but the mandated handoff to unreviewed third-party skills introduces a meaningful transitive trust risk. No direct credential theft, exfiltration, or malicious payload behavior is present in this skill itself.
Confidence: 82%Severity: 52%
Audit Metadata