primitives-showcase
Warn
Audited by Socket on Jul 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The stated purpose matches a workflow/integration-test skill, and there is no clear credential harvesting or external exfiltration in the text. However, it instructs the agent to execute an unseen local scripts/run helper and rely on unspecified MCP tooling, so the actual execution path is not independently verifiable from this skill content.
Confidence: 82%Severity: 72%
Audit Metadata