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.
npx skills add UnboundCompute/security-agent-skills --skill red-teaming-multi-agent-systemsgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/skills/unboundcompute/security-agent-skills/red-teaming-multi-agent-systems)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/red-teaming-multi-agent-systems"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/red-teaming-multi-agent-systems/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/skills/unboundcompute/security-agent-skills/red-teaming-multi-agent-systems"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/red-teaming-multi-agent-systems.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00122 | $0.01591 |
| Opus 5.5 | $0.00049 | $0.00636 |
| Sonnet 5.5 | $0.00024 | $0.00318 |
| Haiku 4.5 | $0.00012 | $0.00159 |
Grade A, and why
red-teaming-multi-agent-systems 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red-teaming multi-agent systems: the edges between agents are attack surface
A single agent has one context to defend. A system of agents has one per agent plus every channel between them, and those channels are the new surface. When one agent's output becomes another's input, and any agent in the chain can be steered by external content, the steering propagates across agents that each "trust" their peer. The vulnerabilities here do not exist in a solo agent; they are born from the wiring.
When to use
- You are reviewing an orchestrator, a crew/swarm, or an agent-to-agent (A2A) protocol where agents route work to each other.
- Any pipeline where one agent's output feeds another agent as instructions.
- Agents share memory, a task queue, or a blackboard, or can spawn or delegate.
Scope check
Test agent systems you own or are authorized to test. Use benign, marked payloads; never drive real privileged actions against systems you do not control. If you can't name the authorization, stop.
The loop
-
Map the topology and the trust edges. Diagram every agent and every directed edge: who can message, spawn, or delegate to whom. Mark the edges that cross a trust boundary, where a lower-trust or externally-influenced agent feeds a higher-privileged one. Each edge where output becomes another agent's instructions is an internal injection channel.
-
Treat every inter-agent message as untrusted content. If agent B acts on agent A's text as instructions, and A can be steered by content it ingests, then an attacker who reaches A reaches B. This is indirect prompt injection with an agent as the carrier: agent-in-the-middle. Test whether a payload planted in A's input changes B's actions.
-
Test delegation and recursion bounds. Can an agent spawn or delegate without a depth, step, or budget cap? Plant a task that makes agents delegate in a cycle or fan out unboundedly. No cap means a recursive delegation loop, which is both a denial-of-service and a denial-of-wallet.
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.
- 1mo ago First seen · 132 lines · 122 tokens per session scan A 48355d4cc076
red-teaming-multi-agent-systems is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,591 once invoked, about $0.0005 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 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.
varlock-claude-skill
Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits.