Show HN: Scan your AI agent's code for tool calls with no checks

Category: security

Tags: ai-security, static-analysis, agent-governance

Score: 7.3/10 (Innovation: 7, Technical: 7, Documentation: 8, Utility: 7)

diplomat-agent-ts is a static analysis tool that scans TypeScript AI agent codebases to detect tool calls (e.g., database writes, payments, email sends) that lack safety guards like rate limits, approval steps, or input validation. It's interesting because it addresses a critical but overlooked security gap in AI agents, offering OWASP mapping, CI integration, and a behavioral SBOM for tracking agent capabilities over time.

Target audience: backend devs, ai-engineers, security-engineers

Repository: https://github.com/Diplomat-ai/diplomat-agent-ts · TypeScript · NOASSERTION · 1 stars

View on Hacker News