detecting-exposed-secrets-files
Warn
Audited by Socket on Aug 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent as a pentest scanner and does not show credential harvesting, covert exfiltration, or untrusted installer behavior. However, it equips the AI agent with active offensive security scanning against remote targets and broad enough tooling to probe exposed secrets, making it high security risk even if not malware.
Confidence: 90%Severity: 79%
Audit Metadata