bb-local-toolkit
Warn
Audited by Socket on Jul 31, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent as an offensive bug-bounty/red-team playbook, but that stated purpose itself grants high-risk exploit capability to an AI agent. Install sources are mostly coherent and same-org/official, so this is not confirmed malware; the main concerns are offensive-security enablement, transitive skill chaining, untrusted-content prompt-injection exposure, and explicit system-prompt-extraction guidance.
Confidence: 93%Severity: 91%
Audit Metadata