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.
Fail4 providerslatest audit Apr 16, 2026
Independent checks from skills.sh's audit partners.
This skill is a security testing playbook for Large Language Models (LLMs), detailing methods for prompt injection and jailbreaking. While educational, it contains a high density of malicious payloads, including instructions to bypass safety guidelines, extract system prompts, and perform data exfiltration. The presence of these patterns could be misinterpreted by an AI agent, leading to unauthorized actions or compromise.
Detected behaviors
2 alerts: gptSecurity
3 issues
3 findings · Score: 69/100