meta-ads
Warn
Audited by Socket on Mar 13, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated purpose and most capabilities are coherent for an ad-management skill, but the trust boundary is problematic because the skill delegates core access and actions to a third-party `social-cli` with unclear provenance from the supplied evidence. Real-world ad account mutations are in-scope and mitigated by an explicit-approval rule, yet the external CLI dependency and credential forwarding keep overall risk elevated.
Confidence: 82%Severity: 74%
Audit Metadata