semantius-deploy-test-maker
Warn
Audited by Socket on May 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's behavior is mostly coherent with its stated purpose: it reads a model, emits a local verification script, and defers live checks to that script. The main concern is install/execution trust: the generated script depends on a `semantius` CLI whose official distribution and provenance were not verifiable from the provided evidence, creating a black-box supply-chain risk. No clear credential harvesting, exfiltration endpoint, stealth behavior, or purpose mismatch is present.
Confidence: 79%Severity: 72%
Audit Metadata