bmad-brainstorming
Warn
Audited by Socket on Aug 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s stated purpose is benign and mostly aligned with local memlog/config handling, but it executes project-local scripts at activation, creating a trust boundary break with the working tree. No clear credential theft, exfiltration endpoint, or malware behavior is shown, yet the install/execution model is riskier than necessary for a brainstorming coach.
Confidence: 84%Severity: 72%
Audit Metadata