ai-safety-and-red-teaming SKILL.md skillB
ai-safety-and-red-teaming from jnpiyush/agentx is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jnpiyush/agentx/ai-safety-and-red-teaming@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jnpiyush/agentx
- Path
.github/skills/ai-systems/ai-safety-and-red-teaming/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Sep 15, 2026
- First version recorded
- Apr 30, 2026
- Size
- 6,239 bytes
- Repository stars
- 18
- License
- Apache-2.0
Defend LLM systems against prompt injection, jailbreaks, data exfiltration, and unsafe output. Covers input/output guardrails (NeMo Guardrails, LlamaGuard 3, ShieldGemma, Azure AI Content Safety, Bedrock Guardrails), red-team frameworks (Microsoft PyRIT, Garak, promptfoo redteam), and Responsible AI controls (groundedness, PII, toxicity, indirect prompt injection).
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# 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 | …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/ai-safety-and-red-teaming@sha256:a1788c32eaf5bc8bThe line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_d2cut2kfx7umjnx7)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 30, 2026 and Sep 15, 2026, about one every 137 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 6,239 B | B | view · diff |
| v1.0.0 | 2026-04-30 | 4f38ce8 | 6,237 B | B | view |
Audit of the latest version
- fail: No script tag (matched: <script)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6239 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
jnpiyush/agentx · 18 stars · license Apache-2.0 · pushed 2026-11-01 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_d2cut2kfx7umjnx7 GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/ai-safety-and-red-teaming GET https://markdownregistry.com/api/v1/blob/a1788c32eaf5bc8b1f76bd6f6360250329a5541acd963dc8566e8ff9a255f26e
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.