vigilantshield

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Master orchestrator for claude-hunterKit — 148 offensive security skills. RED TEAM recon-first pipeline: deep recon → decision matrix → targeted exploit → chain & escalate. 31 escalation paths, 8 stop conditions.

vigilantshield/Claude-HunterKit

MCP server Claude CodeCodexCursor +2

Lets the agent inspect and automate a live Chrome instance through the DevTools protocol: performance traces, network, console. Runs locally from the chrome-devtools-mcp npm package.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Complete bug bounty workflow: recon (subdomain enumeration, asset discovery, fingerprinting, HackerOne scope, source code audit), pre-hunt learning (disclosed reports, tech stack research, mind maps, threat modeling), vulnerability hunting (IDOR, SSRF, XSS, auth bypass, CSRF, race conditions, SQLi, XXE, file upload…

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

AI prompt injection full offensive methodology: direct/indirect injection, roleplay jailbreaks (DAN, AIM), encoding bypass, Unicode smuggling, multi-turn extraction, model-specific payloads.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

LLM endpoint reconnaissance: model API discovery, inference endpoint probing, vector store identification, embedding API detection, and model metadata extraction.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Advanced jailbreaking: roleplay personas (DAN, AIM), encoding obfuscation, multi-turn conditioning, context window reset, and model-specific jailbreak chains.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

System prompt leakage extraction: direct extraction, translation bypass, multi-turn extraction, roleplay persona override, character-by-character extraction.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

RAG poisoning: document-level prompt injection, vector database poisoning, context manipulation via uploads, retrieval bias exploitation, semantic cache poisoning.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

XSS via LLM output, markdown injection, CSV formula injection, code execution via generated scripts, RCE via terminal commands.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

PII extraction, training data memorization probing, API key discovery, internal URL/path enumeration, knowledge boundary probing.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Tool-scope abuse, authority boundary bypass, function misuse, goal hijacking, tool chain escalation.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Goal hijacking, task chain manipulation, sub-agent confusion, privilege escalation, multi-agent collusion.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

MCP server exposure, tool routing abuse, agent overreach via MCP tools, tool output injection, MCP SSRF.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Context window overflow DoS, expensive prompt attacks, recursive self-query loops, API cost amplification.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Endpoint probing, inference API stealing, model architecture fingerprinting, weight extraction via API queries.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Training data injection, fine-tuning manipulation, RLHF poisoning, bias injection, backdoor triggers.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Model API endpoint vulns, inference server misconfig, API key exposure, rate limit bypass, cloud AI service abuse.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Image-to-text injection, audio manipulation, video frame injection, cross-modal prompt injection.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

LLM cookie hijacking, CSRF via LLM actions, OAuth token theft via prompt injection, session reuse.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Memory injection across conversations, prompt chain manipulation, context poisoning, session memory extraction.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Web page content poisoning, email injection, document embedding hijacking, third-party data manipulation.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Adversarial examples, input perturbation, model evasion via text obfuscation, safety classifier bypass.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Membership inference, training data reconstruction, attribute inference from model behavior, confidence analysis.

vigilantshield/Claude-HunterKit

Skill Claude CodeCodex

Context window overflow, token boundary manipulation, attention confusion, KV-cache probing.