ai-redteam
Skill4 starsChanged 5 months agoMITView on GitHub
AI and LLM red-teaming skill for evaluating prompt injection, jailbreak, data exfiltration, tool abuse, agent hijack, RAG poisoning, model denial of service, and unsafe tool-use chains in Gemini, Claude, GPT, and open-weight models. Use to build evaluation harnesses, attack corpora, defensive guardrails, and red-team reports for AI systems you own or are authorized to test.
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Only target models, agents, and applications the user owns or has written authorization to test.
- Distinctive: line 11
Do not produce working malware, CSAM, weapons synthesis, or content that bypasses model safety for harmful real-world outcomes.
- Distinctive: line 12
Treat findings as defensive: every successful attack must ship with a detection and a mitigation.
- Very specific: line 30
Run the harness; record {pass, fail, partial, refusal_quality, leak_evidence}.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Red Team
Authorization Boundary
- Only target models, agents, and applications the user owns or has written authorization to test.
- Do not produce working malware, CSAM, weapons synthesis, or content that bypasses model safety for harmful real-world outcomes.
- Treat findings as defensive: every successful attack must ship with a detection and a mitigation.
Attack Taxonomy
Direct injection: instructions in user input override system policy.Indirect injection: hostile content in retrieved docs, web pages, emails, files, image alt-text, or tool output.Jailbreak: roleplay, hypothetical, encoding, obfuscation, multi-turn drift, persona pinning.Tool abuse: forcing browse, shell, code, or MCP tools to act outside scope (SSRF, file read, command exec).Data exfiltration: leaking system prompt, secrets, embeddings, training data, or per-user memory.Agent hijack: rewriting plans, looping, escalating permissions, calling unintended sub-agents.RAG poisoning: index pollution, ranking manipulation, embedding collisions.Resource exhaustion: token bombs, recursive tool calls, prompt-bomb DoS.
Evaluation Workflow
- Map the AI surface: model, system prompt, tools, retrievers, memory, output sinks, and downstream callers.
- Build a threat model with abuse cases per surface.
- Generate a versioned attack corpus (
attacks.jsonl) with{id, technique, payload, expected_block, severity}. - Run the harness; record
{pass, fail, partial, refusal_quality, leak_evidence}. - Score with attack success rate per technique, mean time to refuse, and blast radius.
Defensive Output
- Input/output classifiers and allow-listed tool schemas.
- Provenance tags on retrieved context; quarantine for untrusted sources.
- Plan-then-execute pattern with human approval on high-impact tools.
- Rate limits, recursion caps, and per-tool budgets.
- Red-team report: top techniques, reproductions, fix owners, regression tests.
Deliverables
surface.md,threats.md,attacks.jsonl,harness/,results.csv,report.md,regression-suite/.
Other versions3 projects use a version of this.
Word for word · 1
- Garyson26/Trident-SecOps-Skills★ 1100% same
Edited · 0
None found.
Wrote their own version · 2
- rade-nugroho/Agentic-Enteprises-Skill★ 9same name
- daemon-blockint-tech/Agentic-Enteprises-Skill★ 8same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository45 other files it gives its agents.
- ai-redteamSkill
- api-security-automationSkill
- assembly-programmingSkill
- bug-bounty-workflowSkill
- claude-mythos-emulationSkill
- cloud-security-automationSkill
- cybersecurity-partnerSkill
- detection-engineeringSkill
- devsecopsSkill
- exploit-developmentSkill
- forensics-triageSkill
- gemini-tool-orchestratorSkill
- go-programmingSkill
- kubernetes-securitySkill
- malware-reverse-engineeringSkill
- multilingualSkill
- offensive-securitySkill
- prompt-enhancementSkill
- python-programmingSkill
- api-security-automationSkill
- assembly-programmingSkill
- bug-bounty-workflowSkill
- claude-mythos-emulationSkill
- cloud-security-automationSkill
- cybersecurity-partnerSkill
- detection-engineeringSkill
- devsecopsSkill
- exploit-developmentSkill
- forensics-triageSkill
- gemini-tool-orchestratorSkill
- go-programmingSkill
- kubernetes-securitySkill
- malware-reverse-engineeringSkill
- multilingualSkill
- offensive-securitySkill
- osint-recon-automationSkill
- prompt-enhancementSkill
- purple-team-automationSkill
- python-programmingSkill
- smart-contract-auditSkill
- soc-operationsSkill
- threat-intel-fusionSkill
- smart-contract-auditSkill
- soc-operationsSkill
- threat-intel-fusionSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.