← All skills

research

100 / 100 · Low risk

Fine to try.

By Encod3d-Sec/TORCH (GitHub) · security · 340 stars · scanned at commit d21b6c9

Vulnerability-research loop toward a novel CVE. Target triage -> attack-surface map -> ranked hypotheses -> investigate (RE / fuzz / audit) -> a finding deepens the loop, a dead-end pivots to a new approach. Uses the full wiki + hunt skillset. Scaffolds and persists state under raw/research/<project>/. Triggers - "research", "find a cve", "analyze this binary/library", "audit this code for vulns".

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'research' ] || [ -L ~/.agents/skills/'research' ]; then echo 'A skill folder named research already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Encod3d-Sec/TORCH' "$d" && git -C "$d" checkout --quiet 'd21b6c94982cec09c88ae9c0e98f4e3865de7148' -- 'skills/research' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/research' ~/.agents/skills/'research' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'research' ~/.claude/skills/'research' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for Encod3d-Sec/TORCH shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/Encod3d-Sec/TORCH.svg)](https://zalavijaysinh.github.io/skilltrust/repos/Encod3d-Sec/TORCH/)

Score history