Custom nuclei templates
SkillSecurityWrite custom nuclei templates to codify a finding into a repeatable, mass-scannable check. Load on "write a nuclei template", turning a manual bug into automation, checking a CVE across many hosts, or regression-scanning. Signals: a reproducible request→match, YAML templates, nuclei.
Use Custom nuclei templates in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add Custom nuclei templates and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the Custom nuclei templates skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by noorqureshi/sploitagent in skills/automation/automation-nuclei-templates/SKILL.md and read by Ahel’s review.
When it applies
You confirmed a bug (or a CVE pattern) and want to (a) find every other affected host and (b) keep a regression check. A nuclei template turns "one request + one match condition" into a scalable, shareable detector.
Why it works
nuclei runs declarative YAML: send request(s), assert matchers on the response. If your finding is expressible as request→observable signal, it's a template — and then it scans thousands of hosts consistently, no manual repetition.
Method
- Capture the minimal repro: the exact request and the unambiguous signal that proves the bug (status, a body string, a header, a reflected marker, response time).
- Write the template:
id,info(name/severity/tags), thenhttp:withmethod,path(use{{BaseURL}}), anypayloads, andmatchers(word/status/regex/dsl). Usematchers-condition: andto avoid false positives; add anextractorto pull the proof. - Reduce false positives: match a signal unique to the vuln (a computed reflection, a specific error), not a generic 200; test against a known-good and known-bad host.
- Validate:
nuclei -t mytemplate.yaml -u https://known-vuln(should hit) and against a safe host (should not). Lint with-validate. - Scale/share: run across your live-hosts list; contribute non-sensitive templates upstream.
Gotchas
- Overbroad matchers = noisy, untrusted results; require a signal that only the vuln produces.
- Interpolate
{{BaseURL}}/variables correctly; hardcoded hosts don't scale. - Destructive checks (writes/DoS) don't belong in a mass template — keep them read-only.
Verify success
The template fires only on genuinely-affected hosts (true on the known-vuln, quiet on the known-good) and extracts a clear proof.
References
nuclei templating guide; nuclei-templates repo (examples); PDTM docs.
Signals
- GitHub stars
- 20
- Forks
- 7
- Last commit
- Sep 2026
Advanced
- Item type
- skill
- Key
automation-nuclei-templates- Source
- github.com/noorqureshi/sploitagent
github.com/noorqureshi/sploitagent
Related picks
Skill · stbenjam
The pick for Dependenciesauditing-python-dependencies
Skill · jeremylongshore
The pick for Dependencieschecking-owasp-compliance
Skill · jeremylongshore
The pick for Web (OWASP)owasp-security
Skill · davila7
The pick for Web (OWASP)gws-shared
Skill · googleworkspace
More in Securitydefi-amm-security
Skill · affaan-m
More in Security