Argus
Black-box, open-source red-team testing for AI agents. Point Argus at any HTTP, gRPC, or browser-using agent endpoint, run 500+ adversarial probes (OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, TAP/PAIR/GCG), get LLM-judged findings as SARIF, gate CI via GitHub Code Scanning. Ships with CLI + GH Action.
A security testing tool that attacks AI applications with 160+ probes including prompt injection and jailbreaks, then grades results using an AI judge and outputs reports in SARIF, JUnit, and HTML formats.
Argus is a tool that tests AI-powered applications for security weaknesses by attacking them the way a real adversary would. You point it at any AI agent that accepts HTTP requests, gRPC calls, or controls a web browser, and it sends hundreds of specially crafted inputs designed to make the agent misbehave, reveal secrets, or bypass its intended restrictions.
The tests are grouped around well-known AI security frameworks, including the OWASP LLM Top 10 (a list of the most common ways AI language models fail) and MITRE ATLAS (a catalog of real-world AI attacks). Argus runs probes that attempt prompt injection, hiding malicious instructions inside documents the agent reads, jailbreaks that build up over multiple turns of conversation, and attacks that conceal content in invisible characters. There are over 160 individual probes in the bundled library.
After each test run, Argus grades the results using a second AI model that acts as a judge. The judge evaluates whether each attack succeeded. Results come out in standard report formats that security and engineering teams already use: SARIF (which drops directly into GitHub Code Scanning), JUnit XML (which can block a build if critical issues are found), and HTML for human reading.
Setting up a scan requires writing a small configuration file that describes your agent's address and authentication method, then running the argus-probe command-line tool. A bundled GitHub Action makes it straightforward to run scans automatically whenever code changes. The repo also includes a deliberately insecure demo agent so you can try everything without connecting to a real system first.
Argus is designed for security testing, not for running inline as a production filter. It is released under the Apache 2.0 License.
Where it fits
- Run a security scan against your AI agent to find prompt injection vulnerabilities before shipping to production.
- Integrate Argus into your CI/CD pipeline via the bundled GitHub Action to automatically block builds when critical AI security issues are found.
- Generate a SARIF report from an Argus scan and upload it directly to GitHub Code Scanning for visibility in pull requests.
- Try out Argus against the bundled demo agent to learn AI security testing without risking your real system.