hunt-burp
Drive Burp Suite over its MCP server as an AI triage + attack layer - review proxy history for signals, replay via Repeater/send,…
N-day / patch-diff workflow - given a CVE/advisory or a suspicious patch, diff pre- vs post-patch to locate the fixed bug, build a PoC for the unpatched version, and run variant analysis for a fresh bug. Triggers - "n-day", "patch diff", "diff the patch", "bindiff".
$ npx -y skills add Encod3d-Sec/TORCH --skill nday --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/ndayContext preview
The summary Claude sees to decide when to auto-load this skill.
N-day / patch-diff workflow - given a CVE/advisory or a suspicious patch, diff pre- vs post-patch to locate the fixed bug, build a PoC for the unpatched version, and run variant analysis for a fresh bug. Triggers - "n-day", "patch diff", "diff the patch", "bindiff".
name: nday description: N-day / patch-diff workflow - given a CVE/advisory or a suspicious patch, diff pre- vs post-patch to locate the fixed bug, build a PoC for the unpatched version, and run variant analysis for a fresh bug. Triggers - "n-day", "patch diff", "diff the patch", "bindiff".
Turn a patched vulnerability into a working PoC, or surface a silently-patched bug. Read [[nday-patch-diffing]] first.
1. **Acquire both versions** - vulnerable + fixed: git tags, release assets, distro packages, or vendor binaries. 2. **Diff:**
3. **Root-cause from the diff** - what the patch *adds* (bounds/auth/sanitization check) reveals what was missing; trace the now-checked value back to attacker input. 4. **Build the trigger** - craft input that reaches the pre-patch unchecked path; reproduce on the vulnerable build; confirm **reachability** in a realistic config. 5. **Variant analysis** - grep / [[codeql]] for the same flawed pattern the patch did not touch -> potential **new** CVE (then hand off to the `disclosure` skill).
Reusable diffing trick or a found variant pattern -> update [[nday-patch-diffing]] (or the matching technique page via `research-ingest`).
Report: target patch, located bug, PoC status, any variant found.
An AI-powered penetration testing and bug-bounty knowledge base and automation harness for Claude Code.
Drive Burp Suite over its MCP server as an AI triage + attack layer - review proxy history for signals, replay via Repeater/send,…
Capture a Burp Suite Repeater request/response as a PoC image (targets/<eng>/poc/) by driving the Burp MCP + the Kali GUI.…
OFFLINE FALLBACK for the claude-md-management plugin - prefer that plugin when it is installed. Audit and improve CLAUDE.md files…
Drive responsible disclosure of a proven finding to a CVE. Package the report, find the vendor contact, report privately,…
Active Directory attack hunting - enumeration to domain dominance. Spray-safe (lockout gate), AS-REP/Kerberoast, ACL + ADCS…
API attack hunting (REST / GraphQL / gRPC) - BOLA/IDOR, BFLA, mass assignment, excessive data exposure, auth/JWT, introspection +…