gpt55-critical-auditor
Warn
Audited by Socket on Aug 9, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is internally consistent as a security audit skill, but its scope is high-risk because it gives an agent Bash plus broad read/write access for adversarial probing. No external installer, credential harvesting, or exfiltration path is shown, so this is not confirmed malware; the main concern is offensive local testing capability and potential overreach.
Confidence: 85%Severity: 58%
Audit Metadata