A developer building AgentGuard, a runtime authorization layer for AI agents, had the implementation independently tested by OpenWorkProof and found two high-severity issues: authorization could be as…
OpenWorkProof Core 1.4.0 and a community DeepSeek Harness plugin have been released, enabling verification of agent work orders and evidence outside the originating system. The update includes a packa…
A developer's blog post argues that cryptographic signatures on AI agent receipts do not guarantee accurate measurements, highlighting the distinction between provenance integrity and measurement inte…
A community-driven specification, OpenWorkProof, defines a protocol for verifying AI agent work through signed, auditable evidence and negative control arms. The protocol addresses the failure model w…