Tool
GitHub - Pryxor/pryxor: Runtime security layer for AI agents. Intercepts every tool calls, decides and execute the real actions without the agent never hold a credential.
Publication date unknown · Discovered github.com
Page published
Publication date unknown · First observed: 11 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Pryxor addresses a core agentic-AI risk — compromised or prompt-injected agents abusing tools and credentials — by brokering tool execution and keeping credentials out of the agent's reach.
Pryxor is an open-source runtime security layer for AI agents published on GitHub that intercepts every tool call, makes authorization decisions, and executes the real actions itself so the agent never holds a credential. The repository includes policy configs, audit logging of APPROVED/BLOCKED/HOLD decisions, encrypted hold payloads, and executors demonstrating destructive-action controls.