ASI01 · 0/3 ranked
Agentic security / 2026
Follow the signal.
Break the boundary.
Agents act, delegate, and remember. Explore the trust boundaries behind their decisions through tools, state changes, and verifiable evidence.
ASI02 · 0/3 ranked
Tool Misuse & Exploitation
ASI03 · 0/3 ranked
Identity & Privilege Abuse
ASI04 · 0/3 ranked
Agentic Supply Chain Vulnerabilities
ASI05 · 0/3 ranked
Unexpected Code Execution (RCE)
ASI06 · 0/3 ranked
Memory & Context Poisoning
ASI07 · 0/3 ranked
Insecure Inter-Agent Communication
ASI08 · 0/3 ranked
Cascading Failures
ASI09 · 0/3 ranked
Human-Agent Trust Exploitation
ASI10 · 0/3 ranked
Rogue Agents
Threat taxonomy: OWASP Top 10 for Agentic Applications 2026. Missions are independently authored training scenarios.