Agentic Security
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
FreeAI Agents5,065 impressions#7 of its week
Agentic Security is an open-source scanner that tests LLMs and AI agents for jailbreaks, multimodal attacks and other vulnerabilities.
- for
- LLM developers, AI security researchers and DevOps teams building AI agents
- pricing
- open source
- license
- Apache-2.0
Key features
- Multimodal Attacks — Test text, image and audio inputs to find cross-modal weaknesses.
- Multi-Step Jailbreaks — Run iterative attack sequences that simulate sophisticated jailbreaks.
- Comprehensive Fuzzing — Generate random inputs to stress-test LLMs and expose edge-case failures.
- API Integration & Stress Testing — Connect to any LLM API and perform high-volume, real-world attack scenarios.
- RL-Based Attacks — Use reinforcement-learning probes that adapt to the model’s defenses.
Use cases
- Detect jailbreak vectors in a newly released LLM before production rollout
- Validate that multimodal AI assistants resist image-based prompt injections
- Run CI-integrated security scans on LLM-backed micro-services
- Benchmark the robustness of custom agentic workflows against iterative attacks
Agentic Security vs alternatives
 Agentic Security |  Fine |  SuperAGI Cloud |  Agent Compass by Future AGI |  AutoAgents | |
|---|---|---|---|---|---|
| Best for | LLM vulnerability scanning and red-team testing | AI agent development platform | Managed AI agent execution | Agent behavior tracking | Agent development in Rust |
| Pricing | Open source | Free | Free | Subscription | Free |
| DevHunt upvotes | 3 | 75 | 43 | 17 | 11 |
| Launched | Feb 2025 | Jan 2023 | Jan 2023 | Nov 2025 | Jul 2025 |
- Agentic Security vs Fine: Focuses on building AI agents rather than scanning them for security flaws
- Agentic Security vs SuperAGI Cloud: Provides cloud-hosted autonomous agents, not a vulnerability scanner
- Agentic Security vs Agent Compass by Future AGI: Creates a truth graph for agents; does not perform automated attack testing
- Agentic Security vs AutoAgents: Rust-based framework for building agents, not a security testing suite
Agentic Security FAQ
How do I install Agentic Security?+
Install via pip with `pip install agentic_security` and run the CLI using `agentic_security` or `python -m agentic_security`.
Can I use Agentic Security in CI pipelines?+
Yes, the tool provides a `ci` command and can be configured with a TOML file to run as part of automated checks.
What data formats are supported for custom prompts?+
You can add CSV files containing a `prompt` column; the tool loads them automatically at startup.
How are attacks defined for a target model?+
Define an HTTP request template (model, messages, etc.) in the config; the placeholder `<<PROMPT>>` is replaced with each attack vector.
Is there support for reinforcement-learning based attacks?+
Yes, the RL-Based Attacks feature lets you craft adaptive probes that evolve during scanning.
What output does the scanner provide?+
After a scan it reports failure rates per module, overall pass/fail status and a summary table of results.
Summarized by DevHunt from github.com · Sep 28, 2026. Details may change; check the official site.
