paid-media-audit
Warn
Audited by Socket on Sep 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core analytics purpose is coherent, and most data access is proportionate, but the skill expands scope by persisting researched context locally and by relying on a `meta-ad-library` tool whose provenance is not established in the skill. Intempt-owned MCP references look legitimate but still carry supply-chain risk due to unpinned external execution. No clear credential theft or overt exfiltration is shown, so this is not malicious, but the unverifiable tool reference and external-content ingestion justify a high security-risk classification.
Confidence: 84%Severity: 74%
Audit Metadata