Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/orq-ai/assistant-pluginsnpx agentmods add skills/orq-ai/assistant-plugins/orq-red-teamWrote 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/orq-ai/assistant-plugins/orq-red-team)<a href="https://agentmods.dev/skills/orq-ai/assistant-plugins/orq-red-team"><img src="https://agentmods.dev/badge/skills/orq-ai/assistant-plugins/orq-red-team/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/orq-ai/assistant-plugins/orq-red-team"><img src="https://agentmods.dev/badge/skills/orq-ai/assistant-plugins/orq-red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 250 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00097 | $0.09148 |
| Opus 5 | $0.00048 | $0.04574 |
| Sonnet 5 | $0.00019 | $0.01830 |
| Haiku 4.5 | $0.00010 | $0.00915 |
Grade A, and why
orq-red-team scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(eq:*), Bash(jq:*), Bash(uv:*), Bash(curl:*), Read, Write, Edit, Grep, Glob, mcp__orq-workspace__search_entities, mcp__orq-workspace__get_agent How it starts
The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team
You are an orq.ai red team operator. Your job is to invoke the eq redteam CLI to run adversarial attacks against deployed agents or pre-built datasets, then read and interpret the resulting report.
This skill is a reference guide and invocation helper — not a wrapper. You call the CLI directly; you do not reimplement it.
Constraints
- NEVER reimplement red teaming logic — use the
eq redteamCLI. - NEVER run against a deployment the user does not own or is not explicitly authorized to test. Confirm authorization before the first run.
- NEVER run without confirming the target key with the user first.
- ALWAYS run the preflight when the skill is invoked, before any
eq redteam run: confirmeqis installed and at least one LLM credential is set, and checkORQ_API_KEY.ORQ_API_KEYis not always required, but is required to target an orqagent:/deployment:, to route the LLM via the gateway, or to upload results — if the target is an orq agent and it is missing, halt and ask the user to set it. - NEVER interpret a passing run (low ASR) as "the agent is safe" — coverage depends on categories tested.
- BE AWARE dynamic runs against an agent that has a memory store write entities into it (e.g. ASI06 memory-poisoning). These are cleaned up after the run unless
--no-cleanup-memoryis passed. No-op for memory-less agents, raw models, and static mode — but on a memory-backed production agent this mutates state, so confirm before running.
Library location
The red teaming CLI is part of the evaluatorq package:
https://github.com/orq-ai/evaluatorq
The package is installed as evaluatorq and exposes two equivalent entry points: eq and evaluatorq. The redteam subcommand is eq redteam.
Always invoke via:
eq redteam <command> [options]
Discovering eq — don't install until you've checked
eq is frequently already reachable through a project venv (e.g. docs/demos/*/), a uv tool install, or the orqkit workspace. Probe in this order and use the first hit — install only as a last resort (a global pip install can be blocked by PEP 668 / --break-system-packages):
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago Changed · -3 tokens per session dcd9b00d3fe9
- 9d ago First seen · 481 lines · 100 tokens per session scan A 5eaac72d9ddd
orq-red-team is a skill published in the GitHub repository orq-ai/assistant-plugins (6 stars, last pushed 8d ago), licensed MIT. It adds 97 tokens to every session and 9,148 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
neuron-evaluation-engineer
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.