deepen-plan
Warn
Audited by Socket on Mar 25, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core task is plausible, but the implementation is over-broad and unsafe for a plan-deepening skill. Its main risk is transitive execution of arbitrary installed skills/agents from local and plugin sources, combined with untrusted-content ingestion and broad autonomous orchestration.
Confidence: 90%Severity: 86%
Audit Metadata