Stats
Actions
Available In
Tags
Plugin
ai-red-teaming
AI/LLM red-teaming team — 2 agents (ai-redteam-lead, adversarial-testing-engineer) for the layer answering 'can this AI system be made to do harm, leak data, or exceed its authority — and how do we harden it?': threat modeling + rules of engagement, the attack taxonomy (OWASP LLM Top 10 2025 + MITRE ATLAS), direct vs indirect prompt injection, jailbreaks (roleplay/encoding/many-shot/crescendo), data exfiltration & training-data extraction, agentic tool-abuse / excessive agency, multimodal attacks, and defense-in-depth remediation. Fluent in automated red-team harnesses (PyRIT, Garak, Promptfoo red-team, Giskard) and likelihood×impact severity. 3 skills, a 2-doc knowledge bank (attack-taxonomy decision tree + 2026 patterns), and 2 templates. Distinct from llm-evaluation-engineering (quality-regression eval), trust-and-safety (content-moderation / T&S policy), and security-engineering (app/infra pentest) — the adversarial AI-security layer over model- and agent-based systems. Requires ravenclaude-core@>=0.7.0.
What's Inside
Agents2
adversarial-testing-engineer
/adversarial-testing-engineer
Use to EXECUTE AI attacks & harden — run jailbreaks/prompt-injection/data-exfiltration, build automated red-team harnesses (PyRIT/Garak/Promptfoo), triage findings by likelihood×impact, drive defense-in-depth remediation. NOT for app/infra pentest (security-engineering).
ai-redteam-lead
/ai-redteam-lead
Use to SCOPE an AI red-team engagement — the threat model, rules of engagement, attack taxonomy (OWASP LLM Top 10 / MITRE ATLAS), the safety-vs-security split, and success/severity criteria. Decision-tree-driven. NOT for eval quality-regression testing (llm-evaluation-engineering).
Skills3
design-ai-redteam-plan
/design-ai-redteam-plan
Scope an AI red-team engagement by threat-modeling the system (assets, attackers, trust boundaries), splitting safety from security, traversing the attack-taxonomy decision tree to a prioritized OWASP LLM Top 10 / MITRE ATLAS attack list, and setting the rules of engagement plus likelihood×impact success and severity criteria. Reach for this when the user asks "how should we red-team this LLM feature?", "what should we attack first?", "is this a safety or a security problem?", or "what are the rules of engagement?". Used by `ai-redteam-lead` (primary).
harden-and-remediate-ai-system
/harden-and-remediate-ai-system
Triage red-team findings by likelihood×impact and drive defense-in-depth remediation — layered input/output guardrails, injection-resistant prompt structure, least-privilege tool scoping, allow-lists, human-in-the-loop on high-impact actions, output-handling hygiene, and rate/cost limits — then retest each fix with the exact attack that found it and bake it into the regression harness. Reach for this when the user asks "we have a pile of red-team findings — what do we fix and how?", "harden our LLM against prompt injection", or "how do we stop the agent from being tricked into tool calls?". Used by `adversarial-testing-engineer` (primary).
run-adversarial-attacks-and-jailbreaks
/run-adversarial-attacks-and-jailbreaks
Execute the prioritized attacks against an AI system within the rules of engagement — direct and indirect prompt injection, jailbreaks (roleplay, encoding, many-shot, crescendo), training-data extraction and data exfiltration, agentic tool-abuse / excessive agency, and multimodal attacks — capturing each as a reproducible payload plus transcript, then automating what repeats into a PyRIT / Garak / Promptfoo red-team / Giskard harness with a scorer and a CI regression gate. Reach for this when the user asks "run the jailbreak and injection attacks", "build an automated red-team suite", or "can our agent be tricked into calling tools it shouldn't?". Used by `adversarial-testing-engineer` (primary).
Stats
Version0.2.0
LanguageHTML
Stars4
Forks1
MaintenanceGood
LicenseMIT
Last Commit
Added
Available In
Safety Signals
Caution
Uses power tools
Uses Bash, Write, or Edit tools
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
