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 jnPiyush/AgentX --skill ai-safety-and-red-teaminggit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/ai-safety-and-red-teaming)<a href="https://agentmods.dev/skills/jnpiyush/agentx/ai-safety-and-red-teaming"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/ai-safety-and-red-teaming/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/jnpiyush/agentx/ai-safety-and-red-teaming"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/ai-safety-and-red-teaming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high YARA Match · line 3 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 36 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
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 | $0.00095 | $0.01367 |
| Opus 5 | $0.00048 | $0.00683 |
| Sonnet 5 | $0.00019 | $0.00273 |
| Haiku 4.5 | $0.00010 | $0.00137 |
Grade A, and why
ai-safety-and-red-teaming 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 11d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Safety and Red-Teaming
Purpose: Stop unsafe input from reaching the model, stop unsafe output from reaching the user, and prove it with adversarial testing.
When to Use This Skill
- Putting an LLM-powered feature in front of external users
- Tools that read untrusted content (email, web pages, uploads, RAG corpora)
- Agents with high-impact tools (file system, payments, prod systems)
- Compliance / regulated domains (health, finance, legal, gov)
- Any release gate that requires red-team evidence
Threat Model (Top Risks, 2026)
| Risk | Description | Likelihood | Impact |
|---|---|---|---|
| Direct prompt injection | User overrides instructions | High | High |
| Indirect prompt injection | Hostile content in retrieved doc, email, web page, image alt-text, OCR'd PDF | Very High | High |
| Jailbreak / persuasion | Multi-turn coercion to bypass policy | High | Medium |
| Data exfiltration | Tool used to leak secrets via DNS / URLs / images | Medium | Critical |
| Tool / RBAC abuse | Agent calls tools beyond user's actual permissions | Medium | Critical |
| Output harm | Toxic, biased, or illegal content | Medium | High |
| Hallucinated grounding | Fabricated citations or facts presented confidently | High | Medium |
| Model supply chain | Tampered open-weights model or fine-tune | Low | Critical |
Defense in Depth
[User input] -> [Input guardrails] -> [System prompt + RAG]
|
v
[Indirect-injection scrubber on retrieved content]
|
v
[Model inference]
|
v
[Tool-call policy gate (allowlist + arg validation)]
|
v
[Output guardrails] -> [User]
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.
- 11d ago First seen · 155 lines · 95 tokens per session scan A ce38db42e443
ai-safety-and-red-teaming is a skill published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 1,367 once invoked, about $0.0005 per session on Opus 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 2026-08-30.
Other skills, from other repositories
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.