agentic-qa-onboard
Warn
Audited by Socket on Oct 26, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's main behavior is coherent onboarding/documentation, and there is no clear credential theft or malicious exfiltration. The key issue is disproportionate transitive trust: the onboarding/setup flow installs extra skills, including some from personal repos, which extends the agent's capability and trust surface beyond a simple tour skill.
Confidence: 89%Severity: 74%
Audit Metadata