OverviewHistoryStatsSecurity
Security
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Independent checks from skills.sh's audit partners.
Pass3 providerslatest audit Sep 6, 2026
Independent checks from skills.sh's audit partners.
The skill provides a comprehensive framework for LLM agent benchmarking and evaluation. It includes legitimate examples of security threats like prompt injection and obfuscation to facilitate adversarial testing. While the skill processes external agent outputs, it lacks high-risk capabilities, and its behaviors are consistent with its purpose as a testing tool.
Detected behaviors
No alerts
No issues