Skill Claude CodeCodex
Drive Decepticon — an autonomous multi-agent red-team framework — over MCP to run authorized penetration tests and bug-bounty engagements end to end, then watch and steer them live from chat. Launch an engagement against a target, poll its transcript to narrate progress, send messages to refocus it, and pull findings…
Skill Claude CodeCodex
Benchmark mode marker — engagement objective is flag capture. Generic engagement rules apply unchanged.
Skill Claude CodeCodex
Stage 2 vulnerability detector playbook. Reads source around CANDIDATE nodes and promotes real bugs to VULNERABILITY + HYPOTHESIS. Read-only. Load at detector-agent startup.
Skill Claude CodeCodex
Stage 5 exploit construction playbook. Weaponizes validated primitives into multi-step chains that reach crown jewels. Load at exploiter-agent startup.
Skill Claude CodeCodex
LLM red team category — full AATMF v3 tactic coverage (T01–T15). Routing skill: read this first to identify which tactic applies, then load the matching sub-skill. Maps to MITRE ATLAS where overlap exists.
Skill Claude CodeCodex
AATMF T1 — Prompt & Context Subversion. Direct + indirect prompt injection, ASCII smuggling, payload-in-image, prompt-leaking via reflection.
Skill Claude CodeCodex
AATMF T2 — Semantic & Linguistic Evasion. Foreign-language pivot, encoded payloads, esolang, fictional framing, jailbreak via translation.
Skill Claude CodeCodex
AATMF T3 — Reasoning & Constraint Exploitation. System prompt override, constraint negation, role-reversal, instruction conflict exploit.
Skill Claude CodeCodex
AATMF T4 — Multi-Turn & Memory Manipulation. Persistent memory injection, conversation-state poisoning, cross-session contamination, ghost-context leak.
Skill Claude CodeCodex
AATMF T5 — Model & API Exploitation. Rate-limit abuse, token-cost amplification, schema bypass, model-version manipulation.
Skill Claude CodeCodex
AATMF T6 — Training & Feedback Poisoning. Data poisoning, RLHF reward hacks, fine-tune-time exfil, embedding poisoning.
Skill Claude CodeCodex
AATMF T7 — Output Manipulation & Exfiltration. Covert channels in output, schema break, exfil via image gen, side-channel via timing.
Skill Claude CodeCodex
AATMF T8 — External Deception & Misinformation. Misinfo generation at scale, persona impersonation, document fabrication, hallucination weaponization.
Skill Claude CodeCodex
AATMF T9 — Multimodal & Cross-Channel. Image steganography → text exec, audio prompt injection, video frame inject, document-with-hidden-text.
Skill Claude CodeCodex
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
Skill Claude CodeCodex
AATMF T11 — Agentic & Orchestrator Exploitation. MCP tool poisoning, agent-to-agent prompt injection, tool-result spoofing, orchestrator state confusion.
Skill Claude CodeCodex
AATMF T12 — RAG & Knowledge Base Manipulation. PoisonedRAG, vector store flood, embedding collision, retrieval-bias attacks.
Skill Claude CodeCodex
AATMF T13 — AI Supply Chain & Artifact Trust. Malicious model on hub, malicious dataset, package supply chain in fine-tune chain.
Skill Claude CodeCodex
AATMF T14 — Infrastructure & Economic Warfare. Endpoint DoS via expensive prompts, model-API account exhaustion, GPU resource starvation, billing weaponization.
Skill Claude CodeCodex
AATMF T15 — Human-AI Coupling. Deepfake escalation, voice clone vishing, deepfake-image-driven social engineering, automation of human-targeted attacks.
Skill Claude CodeCodex
Stage 4 patch generation playbook. Minimal diffs for validated findings with mandatory patchverify. Load at patcher-agent startup.
Skill Claude CodeCodex
Stage 1 broad-spectrum scanner playbook. Sharded sweep over very large codebases producing CANDIDATE nodes for the Detector to reason about. Load at scanner-agent startup.
Skill Claude CodeCodex
Stage 3 triage and verification playbook. Crafts minimal PoCs, runs them with ZFP controls, promotes validated bugs to FINDING nodes with CVSS. Load at verifier-agent startup.
Skill Claude CodeCodex
Bug bounty report formatting for HackerOne, Bugcrowd, Immunefi, and GitHub Security Advisories. Load after validatefinding succeeds and the finding needs to be submitted to a bounty program.