Paid Media Auditor
Warn
Audited by Socket on Oct 25, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill’s purpose is coherent, but its execution model is underspecified. Official ad-platform integrations would be reasonable, yet the skill leaves room for third-party MCP/CLI tooling that could receive valuable advertising credentials and account data. No direct malware or exfiltration behavior is shown, but the ambiguous integration path and unnecessary Bash access create medium security risk.
Confidence: 86%Severity: 56%
Audit Metadata