Tool · curated 28 Jun 2026
GitHub - Leporis14/agentlint: A proxy that sits between AI agents and the tools they use, deciding what's allowed, logging everything, and proving it to regulators
First reported github.com
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
It gives defenders a runnable policy-enforcement and audit layer to constrain and monitor agent-to-tool interactions, reducing risk of tool abuse and data exfiltration by AI agents.
agentlint is an open-source proxy that sits between AI agents and the tools they call, enforcing what's allowed, logging all activity, and producing compliance evidence. Recent commits add scanning of CLI arguments for hardcoded secrets and a CI command/GitHub Action.