Salmon Introduces Execution Verification Infrastructure (EVI) for Securing AI Agents and Autonomous Systems - Hackread
Brief
San Francisco, USA, September 25th, 2026, CyberNewswire
Archipelo today announced Salmon , Execution Verification Infrastructure (EVI) for AI agents and autonomous systems, powered by a cryptographic protocol designed to make execution history verifiable.
Salmon establishes verifiable execution history and state lineage across humans, AI agents, and automation.
The launch follows the OpenAI–Hugging Face incident, in which OpenAI reported that models participating in cybersecurity evaluations circumvented isolation controls, gained internet access, exploited vulnerabilities, accessed third-party systems, collaborated and delegated work across agents, and took actions their developers did not direct.
OpenAI called the incident a “warning shot” and said sophisticated AI systems require safeguards that operate at the speed of the agents themselves.
All credited sources
Highest-trust first. Dates are the publisher's original publish time.
Salmon Introduces Execution Verification Infrastructure (EVI) for Securing AI Agents and Autonomous Systems - Hackread
Salmon Introduces Execution Verification Infrastructure (EVI) for Securing AI Agents and Autonomous Systems Hackread
Salmon Introduces Execution Verification Infrastructure (EVI) for Securing AI Agents and Autonomous Systems
San Francisco, USA, September 25th, 2026, CyberNewswire
Archipelo today announced Salmon , Execution Verification Infrastructure (EVI) for AI agents and autonomous systems, powered by a cryptographic protocol designed to make execution history verifiable.
Salmon establishes verifiable execution history and state lineage across humans, AI agents, and automation.
The launch follows the OpenAI–Hugging Face incident, in which OpenAI reported that models participating in cybersecurity evaluations circumvented isolation controls, gained internet access, exploited vulnerabilities, accessed third-party systems, collaborated and delegated work across agents, and took actions their developers did not direct.
OpenAI called the incident a “warning shot” and said sophisticated AI systems require safeguards that operate at the speed of the agents themselves.
AI agents use credentials, invoke tools, execute code, call APIs, delegate work to other agents, modify infrastructure and change production state.
As these systems operate across multiple actors and systems, the resulting state does not by itself preserve the execution history that produced it.
Salmon is designed to capture execution as signed events and record the state transitions they produce, providing machine-consumable execution evidence for investigation, detection and response, remediation, supervision and accountability across AI security, safety, control and governance systems.
Archipelo is backed by Dell Technologies Capital and technology investors including Zoom CEO Eric Yuan, Andy Bechtolsheim, Bill Tai, David Weisburd, Hack VC, Sangha Capital and Nima Capital.
Its team brings experience spanning NASA, DoD, AWS, Google, Cisco, Meta, Harvard, MIT and Berkeley.
Execution Verification for AI Security and Control
Identity establishes who or what is acting. Authorization determines what an actor may do. Runtime controls determine whether execution should proceed.