Agentic Security is an open-source scanner for finding vulnerabilities in AI agent workflows and large language models by testing them with jailbreaks, fuzzing, multimodal inputs, and adaptive attacks. Developers, researchers, and security teams use it to probe LLM APIs and assess the defenses of AI systems.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/msoedov/agentic_securityWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/msoedov/agentic_security/claude)<a href="https://agentmods.dev/plugins/msoedov/agentic_security/claude"><img src="https://agentmods.dev/badge/plugins/msoedov/agentic_security/claude/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/msoedov/agentic_security/claude"><img src="https://agentmods.dev/badge/plugins/msoedov/agentic_security/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
agentic-security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "agentic-security",
"version": "1.0.0",
"description": "Drive the agesec security harness through a policy-constrained CLI loop."
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 33 tokens a session between them. Each is measured on its own page, and each can be installed alone.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 18d ago First seen · 6 lines scan A 51a279b53542
agentic-security is a plugin published in the GitHub repository msoedov/agentic_security (2,040 stars, last pushed 2d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-19.
agentic-security compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agentic-securitymsoedov/agentic_security | Plugin | 2.0k | 2d ago | Apache-2.0 | A | — | Claude Code |
| skilltotal marketplacepezhik/skilltotal | Plugin | 16 | yesterday | Apache-2.0 | A | — | Claude Code |
| bridgewardbridge-mind/BridgeWard | Plugin | 41 | 6mo ago | MIT | A | — | Claude Code |
| humanizerblader/humanizer | Plugin | 65k | 9d ago | MIT | A | — | Claude Code |
| claude-plugins-official marketplaceanthropics/claude-plugins-official | Plugin | 46k | today | Apache-2.0 | A | — | Claude Code |
| nextjsvercel/next.js | Plugin | 143k | today | MIT | A | — | Claude Code |
| themes-examplegoogle-gemini/gemini-cli | Plugin | 109k | today | Apache-2.0 | A | — | Gemini CLI |