MAESTRO
MAESTRO framework · Multi-Agent Environment, Security, Threat, Risk, & Outcome
A threat-modeling framework from the Cloud Security Alliance for agentic AI that examines risk across seven layers, from the foundation model up to the agent ecosystem.
In our briefings
The claim each of the newest briefings on MAESTRO would have you leave with.
OWASP's AIVSS v0.8 starts from a CVSS v4.0 base score and adds an uplift worth part of the gap between that base and 10. Ten agentic factors, each scored 0, 0.5 or 1, set the share, and an exploit-maturity multiplier scales it, by default 0.97. With the default mitigation factor of 1.0 (no or weak mitigation), all ten worked examples in the document land between 7.1 and 10.0, seven Critical and three High, and a goal-manipulation flaw with a CVSS base of 2.1 comes out at 7.1. The authors read a jump like that as a sign that the agentic deployment context, not the technical flaw, is the main risk driver. On our reading of the formula, a score can only fall below its CVSS base through the mitigation factor, and the document warns that AIVSS scores are not directly comparable to CVSS base scores.
OWASP's AIVSS lifts a CVSS 2.1 agent flaw to 7.1, and all ten worked examples land High or CriticalBI-FIND-2026-2299
Schroeder de Witt and his co-authors argue that security in multi-agent systems is "non-compositional", so "individually safe agents can compose into unsafe systems", and they make it one of their grounds for a new field. The best evidence they offer for it is cited. Jones, Dragan and Steinhardt (2024) paired Claude-3 Opus, which has strict refusal policies, with a jailbroken Llama-2 70B. The frontier model got the hard coding subtasks and the weak model the evasive phrasing, and together they produced vulnerable code 43% of the time, against under 3% for either model alone.
Each agent and each tool call can pass its check while the system fails, an Oxford-led survey arguesBI-FIND-2026-1859
The Agent Name Service has been rebuilt on the domain name system. In version two an agent's name is a software version in front of a domain its publisher controls, in the form ans://v1.0.0.agent.example.com. A registration authority checks control of the domain the way certificate issuers do, then issues two certificates, one public for the server and one private that carries the agent name. Callers find the agent through a DNS record that says which protocol it speaks, A2A, MCP or plain HTTP, and where its description lives. Every code change needs a new version and a new registration. The first draft's design, a directory that resolved a capability to a decentralized identifier, is gone.
The Agent Name Service draft was rebuilt on DNS, with a GoDaddy author, and no standards body has adopted itBI-FIND-2026-0302
›Cited in 15 briefings
Every briefing that discusses this term, newest first.
- OWASP's AIVSS lifts a CVSS 2.1 agent flaw to 7.1, and all ten worked examples land High or Critical
Article · · OWASP AIVSS project · Ken Huang et al. · Oct 22, 2026
- Each agent and each tool call can pass its check while the system fails, an Oxford-led survey argues
Paper · · arXiv · Christian Schroeder de Witt · Apr 29, 2026
- The Agent Name Service draft was rebuilt on DNS, with a GoDaddy author, and no standards body has adopted it
Draft · · IETF Datatracker · Scott Courtney et al. · Apr 13, 2026
- AAGATE maps NIST's AI risk framework onto Kubernetes, and its paper never times the 'millisecond kill switch'
Paper · · arXiv · Ken Huang et al. · Oct 29, 2025
- A 'provable' bound on agent-memory injection assumes independent layers and fills in none of its detection rates
Paper · · arXiv · Ken Huang et al. · Aug 17, 2025
- DIRF credits its anti-cloning controls with a jump from near 0% to over 90%; no test in the paper applies them
Paper · · arXiv · Hammad Atta et al. · Aug 2, 2025
- QSAF’s failure example shows ChatGPT asking for clarification
Paper · · arXiv · Hammad Atta et al. · Jul 21, 2025
- Function-calling models over-approve unsafe MCP calls; MCIP tests an offline classifier on synthetic chats
Paper · · arXiv · Huihao Jing et al. · May 20, 2025
- The first Agent Name Service paper puts capabilities in the name and leaves protocol translation and governance out
Paper · · arXiv (cs.CR preprint 2505.10609) / OWASP Agentic Security Initiative · Ken Huang et al. · May 15, 2025
- An MCP gateway can do OAuth for servers that have none; this one passes them a user header
Paper · · arXiv · Ivo Brett · Apr 28, 2025
- ATFAA names identity inheritance as an agent threat and answers it with existing cloud policy tools
Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 28, 2025
- An A2A threat model flags the Agent Card as an attack path, and its example flow never passes on the user's identity
Paper · · arXiv · Idan Habler et al. · Apr 23, 2025
- OWASP's multi-agent threat guide finds the hop where a user's permission check drops out, but names no fix
Article · · OWASP GenAI Security Project · OWASP Agentic Security Initiative · Apr 22, 2025
- An early MCP security checklist was never tested, and the protocol has since adopted only part of it
Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 11, 2025
- MAESTRO names your AI agents' identity threats and leaves designing the controls to you
Article · · Cloud Security Alliance · Ken Huang · Feb 6, 2025
Related terms
What appears alongside MAESTRO in the same briefings.
MITRE ATLASJSON-RPC 2.0ANSQorvex Security AI FrameworkHIPAAIntuitAutoGPTOpen Policy Agent