codeprobe-security
Warn
Audited by Socket on Apr 10, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated purpose matches its code-scanning behavior, but it is a dual-use AI security tool and combines untrusted code ingestion with Bash access, creating meaningful prompt-injection and execution risk. Install trust concerns are limited to same-publisher curl|bash hygiene rather than clear malicious distribution.
Confidence: 87%Severity: 74%
Audit Metadata