continuous-llm-red-teaming-with-promptfoo

continuous-llm-red-teaming-with-promptfoo is a skill for Claude Code, Codex from adriannoes/awesome-agentic-ai. It costs 56 tokens per session (2,360 once invoked), scanned A, original, MIT.

A setup for repeatedly testing an AI application against attacks such as jailbreaks and prompt injection. It uses Promptfoo and DeepTeam to run adversarial tests in continuous integration, the automated checks that run when code changes.

In plain words
What is it for?
Use it to red-team authorized AI applications, test against OWASP LLM and agentic-risk categories, run security checks on each commit, and fail builds when vulnerabilities regress.
Why use it?
AI applications can become less safe after a prompt, model, data source, tool, or guardrail changes. Repeating the same attack tests helps detect when a previously fixed weakness returns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to red-team authorized AI applications, test against OWASP LLM and agentic-risk categories, run security checks on each commit, and fail builds when vulnerabilities regress.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo
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.

Any agent
npx skills add adriannoes/awesome-agentic-ai --skill continuous-llm-red-teaming-with-promptfoo
Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for continuous-llm-red-teaming-with-promptfoo

README.md
[![agentmods](https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo/github.svg)](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo)
Your own site
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo/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.

agentmods 80×15 button for continuous-llm-red-teaming-with-promptfoo

Your own site · 80×15
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/continuous-llm-red-teaming-with-promptfoo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 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 2
    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 System Prompt Leakage · line 92
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
  • medium MCP Rug Pull · line 46
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
  • medium Data Exfiltration · line 87
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 5.1 $0.00056 $0.02360
Opus 5 $0.00028 $0.01180
Sonnet 5 $0.00011 $0.00472
Haiku 4.5 $0.00006 $0.00236

Measured 12d ago against content hash b342d31300cb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

continuous-llm-red-teaming-with-promptfoo 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/continuous-llm-red-teaming-with-promptfoo/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Continuous LLM Red Teaming with Promptfoo

Authorized Use Only: Run these adversarial probes only against LLM applications and endpoints you own or are explicitly authorized to test. Generated attack payloads (jailbreaks, prompt injections, harmful-content elicitation) are adversarial inputs; sending them to third-party services without permission may violate terms of service.

Overview

Promptfoo is an open-source LLM evaluation and red-teaming framework (used by OpenAI and Anthropic per its README) that generates adversarial test cases, runs them against your model/agent, and grades the responses. DeepTeam (by Confident AI) is a complementary open-source framework offering 50+ ready-to-use vulnerabilities and 10+ research-backed attack methods. Together they let you treat LLM security as a regression test: every commit re-runs the same adversarial suite, and the pipeline fails when a previously-safe behavior regresses.

This matters because LLM applications change constantly — prompts, models, RAG sources, tools, and guardrails all drift. A jailbreak that was patched last sprint can silently return after a prompt edit or a model upgrade. Promptfoo maps its plugins directly onto the OWASP LLM Top 10 (owasp:llm) and OWASP Agentic (owasp:agentic) presets, and onto MITRE ATLAS, so the suite tracks recognized risk taxonomies. The core threat addressed here is AML.T0051 — LLM Prompt Injection (MITRE ATLAS): adversarial instructions that override the application's intended behavior. This skill follows the Promptfoo red-team docs (https://www.promptfoo.dev/docs/red-team/) and DeepTeam docs (https://www.trydeepteam.com/docs/getting-started), and aligns to NIST AI RMF MANAGE-4.1 (post-deployment monitoring and feedback to manage AI risk).

When to Use

  • When you need continuous, automated red-teaming of an LLM app in CI/CD rather than one-off manual tests.
  • When you want to enforce a security gate: block merges that introduce or reintroduce jailbreak/injection vulnerabilities.
  • When mapping coverage to OWASP LLM Top 10 / OWASP Agentic / MITRE ATLAS for compliance reporting.
  • When comparing the security posture of two models or prompt versions side by side.
  • When tracking vulnerability regression over time across releases.

Read the full file on GitHub · 210 lines

Files

What ships with it

4 files 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.

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. 12d ago First seen · 210 lines · 56 tokens per session scan A b342d31300cb

Subscribe to this mod's changes

continuous-llm-red-teaming-with-promptfoo is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 56 tokens to every session and 2,360 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

continuous-llm-red-teaming-with-promptfoo

Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets, failing the build when jailbreak or injection vulnerabilities regress. Use for continuous adversarial testing in CI/CD, a merge-blocking security gate, or…

Youngmaidainon/Agent-Level-Up · 92 tokens

github-actions

Use when authoring or fixing GitHub Actions CI/CD — workflows under .github/workflows, triggers, job matrix, caching, token permissions, OIDC cloud deploys, environment gates, reusable workflows. NOT the Dockerfile or image build strategy (that is docker), NOT the branching model (that is git-workflow), NOT release…

ericrisco/rsc-harness · 81 tokens

Verification & Quality Assurance

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

ruvnet/ruflo · 36 tokens

playwright-testing

E2E testing with Playwright - Page Objects, cross-browser, CI/CD.

alinaqi/maggy · 20 tokens

terraform-skill

Terraform infrastructure as code best practices.

Agent-Threat-Rule/agent-threat-rules · 10 tokens

implement

Use when an approved plan and task list exist and it is time to turn them into working, tested code — the SDD phase after analyze and before verify. Enforces TDD: a failing test comes before the code that makes it pass, one task at a time, appended to a progress ledger that survives compaction. Delegates test tooling…

ericrisco/rsc-harness · 123 tokens