sesame-onboard
Warn
Audited by Socket on Jul 3, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's main behavior matches its stated AWS onboarding purpose and shows good restraint around secrets, so it does not look malicious. However, it relies on a curl|sh installer with mutable/unpinned behavior, optional checksum skipping, and transitive skill installation, which makes the install and execution trust materially risky for an AI agent skill.
Confidence: 88%Severity: 64%
Audit Metadata