sub-cli
Warn
Audited by Socket on Sep 26, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s capabilities fit a Substack management tool, but its trust model does not. It asks the agent to use a cookie-handling third-party CLI whose official provenance could not be verified, creating notable supply-chain and credential-forwarding risk despite otherwise coherent purpose and scoped instructions.
Confidence: 84%Severity: 74%
Audit Metadata