Argus Red shows an AI CLI for security scans and pen tests
Argus Red argues that public AI models from Anthropic and OpenAI are built to refuse offensive security tasks, while specialized cyber models are usually limited to . That can leave small and mid-sized companies without strong AI help for finding serious weaknesses. Many current AI security tools still sit on top of general models, so they inherit the same refusals.
This tool uses a model on ten years of contests. It will not be open to everyone, but the goal is to make this kind of tool available to responsible smaller companies, not only large enterprises. It runs through a CLI with two modes.
Security scan is a read-only check of a local codebase and only reports issues it can connect to a specific file and line. Pen test is an active mode that tests systems from an attacker-like angle.
Key points
- Public AI models often refuse offensive security tasks.
- Specialized cyber AI tools are usually gated for .
- Argus Red uses a model on security challenges.
- Security scan checks local code in read-only mode and reports file-and-line evidence.
- Pen test actively probes systems from an attacker-like perspective.