browser-verifier — Claude Code skill: what it does, how to install
browser-verifier takes a client-side finding backed by curl evidence and settles whether the payload fires in a real browser. Useful before an XSS report goes out.
no license ★ 1,298 updated 2026-06-12
npx skills add H-mmer/pentest-agents --skill browser-verifier -a claude-codeWhat browser-verifier does
The skill loads a client-side finding so one question gets answered: does the payload actually run in a browser? XSS, DOM sinks, postMessage and prototype pollution all go through it. A response body that echoes your input proves very little, because CSP, framework auto-escaping, a SPA that renders differently or a WAF challenge aimed at the browser request can each stop execution.
A curl header check comes first, to see whether Cloudflare sits in front of the target. Then the camofox stealth browser starts with ../../tools/camofox_ctl.sh start, and the payload URL loads in a tab driven over http://localhost:9377/tabs. Detection does not lean on alert(): dialog hooks, a DOM marker such as XSS-FIRED, or an out-of-band callback. With a strict CSP, preload links and DNS prefetch carry the exfiltration instead.
Three verdicts come back: BROWSER_CONFIRMED, BROWSER_REJECTED, and BROWSER_PARTIAL when the code runs but data cannot leave, which lowers severity. A screenshot lands in evidence/, and the JSON output points back at the original finding. A finding is not dead because alert(1) stayed silent: the later detection tiers have to come back empty first.
What it helps with
- rule out an XSS finding that reflects but never executes
- back a confirmed execution with a DOM snapshot and a screenshot
- work out why a payload stays silent: CSP, escaping, WAF, wrong context
- downgrade a finding that runs but cannot exfiltrate
- keep the verdict and the finding reference in the JSON output
Example prompts for the agent
- Check the client-side finding from the report in a real browser: does the payload execute or not?
- Run
/hunton this target and hand the client-side findings to browser-verifier. - The payload reflects in
curland looks like XSS. Prove or disprove it in a browser and save the screenshot underevidence/.
How to install browser-verifier
1Skills CLI (Vercel)
npx skills add H-mmer/pentest-agents --skill browser-verifier -a claude-code2Manually: put the files in place
~/.claude/skills/agent-browser-verifier/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agent-browser-verifier/
1Skills CLI (Vercel)
npx skills add H-mmer/pentest-agents --skill browser-verifier -a codex2Manually: put the files in place
.agents/skills/agent-browser-verifier/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add H-mmer/pentest-agents --skill browser-verifier -a cursor2Manually: put the files in place
.cursor/skills/agent-browser-verifier/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install H-mmer/pentest-agents providers/cursor/.cursor/skills/agent-browser-verifier2Manually: put the files in place
.github/skills/agent-browser-verifier/SKILL.md1Skills CLI (Vercel)
npx skills add H-mmer/pentest-agents --skill browser-verifier -a gemini-cli2Platform CLI
gemini skills install https://github.com/H-mmer/pentest-agents --path providers/cursor/.cursor/skills/agent-browser-verifierManually: put the files in place
.devin/skills/agent-browser-verifier/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about browser-verifier
How do I install browser-verifier in Claude Code?
Run npx skills add H-mmer/pentest-agents --skill agent-browser-verifier -a claude-code. The skill lands at ~/.claude/skills/agent-browser-verifier/SKILL.md.
What does browser-verifier do?
It runs a client-side finding in a real browser and returns BROWSER_CONFIRMED, BROWSER_REJECTED or BROWSER_PARTIAL, along with a DOM snapshot and a screenshot. /hunt and /validate dispatch it automatically for client-side vulnerability classes.
Why does an XSS payload reflect in curl but never run in the browser?
CSP, output escaping in the framework, a WAF that challenges the browser request, or a context where the payload never executes. The skill narrows it down to one cause and records it in the verdict.