What is aio-agent-threats-reference?

A semantic search and reading tool for an encyclopedia of AI-agent attacks and defenses. Semantic search finds articles by meaning rather than requiring an exact keyword.

Use it to research prompt injection, MCP or tool poisoning, memory poisoning, multi-agent attacks, jailbreaks, coding-agent supply-chain risks, and defensive techniques.

It helps you locate the full article on a particular threat or defense without browsing every volume. It is intended for lookup, not for guiding a complete security engagement.

aio-agent-threats-reference — Skill for Claude Code by aiocean

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add aiocean/claude-plugins

Claude Code

/plugin install aio-agent-threats

Made for: Claude Code.

Or install aio-agent-threats, the plugin that ships this one along with the rest of its 2 skills.

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/skills/aiocean/claude-plugins/aio-agent-threats-reference/github.svg)](https://agentmods.dev/skills/aiocean/claude-plugins/aio-agent-threats-reference)

Your own site

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

Per session 147 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 893 The whole file, excluding the scripts and references it only reads on demand.

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.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00147	$0.00893
Opus 5.5	$0.00059	$0.00357
Sonnet 5.5	$0.00029	$0.00179
Haiku 4.5	$0.00015	$0.00089

Measured 17d ago against content hash 58baf20285b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aio-agent-threats-reference 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/skills/aio-agent-threats-reference/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI-Agent Attack-Vector Reference

Semantic-search lookup over the aio-agent-threats corpus. This skill retrieves and reads; for a guided engagement workflow use the sibling aio-agent-threats advisor skill.

The corpus lives in the sibling skill folder ${CLAUDE_PLUGIN_ROOT}/skills/aio-agent-threats/: volume-NN-*/ directories, with search scripts in scripts/.

Lookup Workflow

1. Search by meaning

cd "${CLAUDE_PLUGIN_ROOT}/skills/aio-agent-threats/scripts" && npx tsx search-vectors.ts "<what you're looking for>" --top 6 --json
# first run only, if embeddings.json is missing: npx tsx build-embeddings.ts

Returns ranked {title, volume, file, score}. Read the full file for the top hits — the file field is the path under ${CLAUDE_PLUGIN_ROOT}/skills/aio-agent-threats/.

2. Browse a volume

List and read articles directly:

ls "${CLAUDE_PLUGIN_ROOT}/skills/aio-agent-threats/volume-03-tool-and-mcp/"

Vol	Focus
01 foundations	attack-surface taxonomy, instruction/data channel, kill chain, OWASP/NIST crosswalk, trust boundaries
02 prompt-injection	direct, indirect, cross-modal, system-prompt leakage, obfuscation, delivery
03 tool-and-mcp	tool poisoning, rug-pull, shadowing, line-jumping, excessive agency, MCP CVEs
04 memory-and-context	MINJA, AgentPoison, RAG poisoning, persistent false beliefs, cross-session, misattribution gap
05 multi-agent	contagious poisoning/worms, A2A trust, orchestrator hijack, cascading failures, protocol attacks
06 jailbreak-evasion	Crescendo/STAC, Echo Chamber, roleplay/DAN, encoding/GCG, many-shot, policy puppetry
07 supply-chain-exfil	coding-agent weaponization, repo poisoning, exfil channels, real incidents, espionage case, model supply chain
08 defense-hardening	detection, spotlighting, dual-LLM/CaMeL, least-privilege, provenance/attestation, defense-in-depth

3. Read the article

Each article carries: Core Concept · Origin/First Seen · How It Works · Attack Surface · Weaponization (lab) · Real-World Instances · Detection · Mitigations · Related Vectors · References. Every factual claim carries a source URL and a HIGH/MEDIUM/LOW confidence label — carry that label through into whatever you report.

Read the full file on GitHub · 55 lines

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 · 55 lines · 147 tokens per session scan A 58baf20285b0

Subscribe to this mod's changes

aio-agent-threats-reference is a skill published in the GitHub repository aiocean/claude-plugins (4 stars, last pushed 16d ago), licensed MIT. It adds 147 tokens to every session and 893 once invoked, about $0.0006 per session on Opus 5.5. 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-reference next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aio-agent-threats-referenceaiocean/claude-plugins	Skill	4	16d ago	MIT	A	147	Claude Code
eval-hooksFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	115	Claude Code
design-patternsFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	59	Claude Code
eval-agentsFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	80	Claude Code
eval-skillsFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	60	Claude Code
source-command-audit-whitepapersFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	26	Claude Code, Codex
audit-agents-skillsFlorianBruniaux/claude-code-ultimate-guide	Skill	6.4k	today	CC-BY-SA-4.0	A	41	Claude Code