What is aio-agent-threats?

A local reference and search plugin about security attacks against AI agents, including prompt injection, tool and MCP poisoning, memory poisoning, jailbreaks, and coding-agent supply-chain attacks. Each topic is paired with defenses and source links with confidence labels.

Use it to research threats to LLM apps, tool-calling agents, MCP systems, retrieval or memory agents, multi-agent systems, and coding agents.

It gives developers a searchable place to study how an agent can be manipulated and how to detect or reduce those risks. The source links and confidence labels help distinguish supported claims from less certain ones.

aio-agent-threats — Plugin for Claude Code by aiocean/claude-plugins

Install

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.

Clone the repo

git clone --depth 1 https://github.com/aiocean/claude-plugins

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/aiocean/claude-plugins/aio-agent-threats/github.svg)](https://agentmods.dev/plugins/aiocean/claude-plugins/aio-agent-threats)

Your own site

<a href="https://agentmods.dev/plugins/aiocean/claude-plugins/aio-agent-threats"><img src="https://agentmods.dev/badge/plugins/aiocean/claude-plugins/aio-agent-threats/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.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/aiocean/claude-plugins/aio-agent-threats"><img src="https://agentmods.dev/badge/plugins/aiocean/claude-plugins/aio-agent-threats.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured The manifest loads nothing itself; its 2 skills cost 280 tokens a session between them.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

aio-agent-threats 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 17d 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.

plugins/aio-agent-threats/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "aio-agent-threats",
  "description": "Attack-first reference for AI-agent security with local semantic search \u2014 how current AI agents (LLM apps, tool-calling agents, MCP servers, RAG/memory agents, multi-agent systems, coding agents) are manipulated and attacked, each vector paired with detection + mitigation. 46 articles in 8 volumes: prompt injection (direct/indirect/cross-modal), tool & MCP poisoning (TPA, rug-pull, shadowing, MCP CVEs), memory & context poisoning (MINJA, AgentPoison, RAG poisoning), multi-agent attacks (ARCJ, worms, orchestrator hijack), jailbreaks (Crescendo, Echo Chamber, many-shot, policy puppetry, GCG), coding-agent supply-chain (Nx s1ngularity, repo poisoning, exfiltration, real incidents), and defense-in-depth (spotlighting, dual-LLM, CaMeL, least-privilege). Every claim carries a source URL and a HIGH/MEDIUM/LOW confidence label. 2 skills: aio-agent-threats (advisor workflow), aio-agent-threats-reference (encyclopedia lookup).",
  "version": "1.0.0",
  "author": {
    "name": "aiocean"
  },
  "repository": "https://github.com/aiocean/claude-plugins",
  "license": "MIT"
}

Contents

What it installs

The manifest is a name and a version. 2 skills travel with it, and installing the plugin installs all of them — 280 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Changes

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.

17d ago First seen · 11 lines scan A f376342115cb

Subscribe to this mod's changes

aio-agent-threats is a plugin published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 16d ago), licensed MIT. 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 2026-10-26.

Building agents Claude Code Security ai-assistant ai-coding anthropic claude cli-tools

aio-agent-threats next to 6 plugins from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aio-agent-threatsaiocean/claude-plugins	Plugin	4	16d ago	MIT	A	—	Claude Code
ccboardFlorianBruniaux/claude-code-ultimate-guide	Plugin	6.4k	today	CC-BY-SA-4.0	A	—	Claude Code
claudekitduthaho/claudekit	Plugin	97	3mo ago	MIT	A	—	Claude Code
humanizerblader/humanizer	Plugin	68k	3d ago	MIT	A	—	Claude Code
claude-plugins-official marketplaceanthropics/claude-plugins-official	Plugin	47k	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