security
AI Red-Team Auditor — continuous adversarial testing for agents
Continuous adversarial testing for LLM apps: prompt injection, jailbreaks, data leakage, tool abuse, memory poisoning, MCP tool poisoning — with CI gating, OWASP LLM/ASI coverage matrix, and false-po…
$19
Quick answer
Continuous adversarial testing for LLM apps: prompt injection, jailbreaks, data leakage, tool abuse, memory poisoning, MCP tool poisoning — with CI gating, OWASP LLM/ASI coverage matrix, and false-positive tracking.
What this skill does
Continuous adversarial testing for LLM apps: prompt injection, jailbreaks, data leakage, tool abuse, memory poisoning, MCP tool poisoning — with CI gating, OWASP LLM/ASI coverage matrix, and false-positive tracking.
Get AI Red-Team Auditor — continuous adversarial testing for agents
$19, one-time — drops into .claude/skills/.