Garyson26/Trident-SecOps-Skills / skills/ai-redteam
ai-redteam
VerifiedAI 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.
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/.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |