InnerVault

Library

85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.

Results

4 results with any of your words Clear search and filters
  1. Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astra, GPT-6.1 SoL, Opus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5, Deepseek V4, Deepseek Flash, DeepSeek V4.1 Pro / Flash, Qwen 3.8 MAX, Qwen 3.8 Omni-Flash, Qwen 3.7 etc

    Stale GitHub, motan1337 16 ★MITUpdated 20 days ago

    git clone https://github.com/motan1337/universal-bypass-for-claude-chatgpt-qwen-deepseek-llm-claude-code-codex.git
  2. cleantv

    Skills

    Remove ads from the Google TV / Android TV home screen and speed the TV up over ADB, no root. Claude Code skill: debloat, clean launcher, picture and sound calibration, YouTube throttling bypass. One command undoes every change.

    Stale GitHub, JohnWayneeee 44 ★MITUpdated 11 days ago

    git clone https://github.com/JohnWayneeee/cleantv.git
  3. Offensive security toolkit for Claude Code covering red team, exploit dev, AD attacks, EDR bypass, mobile pentest

    Stale GitHub, hypnguyen1209 401 ★MITUpdated 26 days ago

    git clone https://github.com/hypnguyen1209/offensive-claude.git
  4. One word — NULL200OK — turns any AI agent (Claude Code, Cursor, Codex) into a disciplined bug-bounty hunter. A single SKILL.md condensing 6 offensive-security repos: recon, 12+ vuln playbooks, exploit chains, Web3/Immunefi, WAF bypass, triage & HackerOne/Bugcrowd reporting.

    Stale GitHub, NULL200OK 5 ★MITUpdated 9 days ago

    git clone https://github.com/NULL200OK/null200ok-bug-bounty-skill.git

Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.