research-new-attack-classes

A research workflow for finding new attack classes affecting agentic AI and MCP systems. It compares primary-source research with the existing AVE records and labels each result as covered, a variant, or new.

In plain words
What is it for?
Periodic threat reviews, checking major disclosures or new research, deciding whether coverage is missing, and opening a GitHub issue for a genuinely new class.
Why use it?
It keeps the detection record set aligned with documented threats without adding duplicate categories just to increase the count.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/aveproject/ave/research-new-attack-classes
Any agent
npx skills add aveproject/ave --skill research-new-attack-classes
Clone the repo
git clone --depth 1 https://github.com/aveproject/ave

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,730 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02730
Opus 5 $0.00000 $0.01365
Sonnet 5 $0.00000 $0.00546
Haiku 4.5 $0.00000 $0.00273

Measured 2d ago against content hash e47bb3bfc39a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-new-attack-classes 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 2d 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.

.claude/skills/research-new-attack-classes/SKILL.md · 278 lines

How it starts

The opening of the file, as written. The whole thing — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.

research-new-attack-classes

Keep AVE current with the real threat landscape. This skill researches agentic AI / MCP attack classes from primary sources, benchmarks each against the existing AVE record set, and for every class decides one of three outcomes: ALREADY COVERED, VARIANT OF EXISTING, or NEW CLASS.

For NEW CLASS only, it opens a GitHub issue and hands off to add-ave-record.

This skill never pads. It maps to distinct behavioral classes that exist in cited research. If a "new" attack is just a textual variant of a class AVE already covers, it is logged as a variant, not a new record.


When to run this

  • Monthly cadence (the field moves fast — set a recurring reminder)
  • After a major disclosure (a new CVE, a new OX/Invariant/HiddenLayer report)
  • After a new academic taxonomy or benchmark paper drops
  • Before a release (close the gap deliberately)

Do NOT run this to hit a record-count target. Run it to stay current. There is no quota. The right number of records equals the number of distinct behavioral classes that exist — no more.


Inputs

  • The current record set in records/*.json
  • The schema in schema/ave-record.schema.json
  • LANGUAGE.md (attack_class vocabulary, behavioral_fingerprint discipline)
  • docs/adr/0001-behavioral-fingerprints.md (the no-signatures rule)

The pipeline — five phases

Phase 1: Research (gather, do not judge yet)

Search primary sources only. Rank by authority:

  1. MITRE ATLAS (atlas.mitre.org) — the AI-specific ATT&CK. The most authoritative existing enumeration of adversarial AI tactics and techniques. Treat it as BOTH a primary source AND a benchmark target. Capture the ATLAS technique ID (AML.Txxxx) for every candidate that maps to one — these IDs go in the AVE record for cross-referencing.
  2. CVE/NVD entries and vendor disclosures (OX Security, Invariant Labs, HiddenLayer, Unit 42, Snyk, Trail of Bits)
  3. Peer-reviewed / arXiv taxonomies and benchmarks (MCPSecBench, MCP-SafetyBench, MCPTox, Formal Security Framework, Hou et al. lifecycle taxonomy, parasitic toolchain studies)
  4. OWASP updates (MCP Top 10, Agentic AI Top 10, AIVSS, AIBOM)
  5. Microsoft / Google / NSA / NIST taxonomy and guidance updates (note: ATT&CK proper for any technique that crosses into conventional TTPs)
  6. Framework changelogs and security advisories (MCP spec, OpenClaw, etc.)

Read the full file on GitHub · 278 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.

  1. 2d ago First seen · 278 lines · 0 tokens per session scan A e47bb3bfc39a

Subscribe to this mod's changes

research-new-attack-classes is a skill published in the GitHub repository aveproject/ave (17 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,730 tokens. 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 2026-08-30.