OWASP Agent Security Regression Harness
What it is
A vendor-neutral CLI tool for running executable security regression tests against agentic applications and MCP-integrated systems. It validates that changes to prompts, models, or tools do not reintroduce known security failures by executing scenarios and asserting expected outcomes against execution traces.
The problem it solves
Lack of executable, reproducible security regression testing for agentic applications and MCP systems, making it difficult to verify that changes do not reintroduce known security failures.
What you could use it for
- Verifying that prompt or model updates do not reintroduce known agent security vulnerabilities
- Testing MCP integrations for unauthorized tool calls or data exfiltration
- Generating machine-readable security test results for CI/CD pipelines
- Auditing agent behavior against pre-recorded execution traces
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.