Skip to content
Diagnosis · Security

probe

Integrating OWASP ZAP/Burp Suite/Nuclei, planning penetration tests, executing DAST, and scanning for vulnerabilities.

by simotagithub.com/simota/agent-skills ↗Source ↗MIT73 repo stars

Testing what is locked and what isn’t

Add it to your AI

View source
Works with
ClaudeChatGPTGeminiClaude CodeCodexCursorCopilotGemini CLI
Setup
Upload one file
About a minute in Claude. One command in coding tools.
Contains
Instructions only
Text files — no scripts or programs.
Maintained
Last change 18 Sept 2026
On the repository’s main branch.
Check
Nothing found by our check

What it does

COLLABORATION_PATTERNS: - Sentinel -> Probe: Static analysis findings for runtime validation - Builder -> Probe: Application endpoints for security testing - Gear -> Probe: Deployment configs and environment details - Breach -> Probe: Red team scenarios requiring DAST validation - Probe -> Sentinel: Dynamic findings to

Read more

refine static rules - Probe -> Builder: Remediation specs with SLA timelines - Probe -> Triage: Critical vulnerabilities (CVSS >= 9.0) for incident response - Probe -> Radar: Security regression test cases - Probe -> Vigil: Confirmed exploit patterns for detection rule creation - Probe -> Canvas: Threat models and attack path visualizations

What it can touch

  • No script files in its folder

    Its folder holds text, not programs. It changes how your AI works; it does not bring code of its own.

    How we know

    Listed the 16 files in the skill’s folder on GitHub; none is a script or program.

  • 7 smaller things worth knowing

    Has notes hidden from people (HTML comments) that your AI still reads; Refers to a credentials file (SSH keys, cloud logins, tokens); Tells your AI to open private keys or password stores; Contacts a server by raw IP address; and more. Usually legitimate — listed so nothing is hidden.

    How we know

    Has notes hidden from people (HTML comments) that your AI still reads — SKILL.md line 6; Refers to a credentials file (SSH keys, cloud logins, tokens) — reference/api-dast.md line 24; Tells your AI to open private keys or password stores — reference/mobile-dast.md line 94; Refers to a credentials file (SSH keys, cloud logins, tokens) — reference/nuclei-templates.md line 54; Refers to a credentials file (SSH keys, cloud logins, tokens) — reference/vulnerability-testing-patterns.md line 17; Contacts a server by raw IP address — reference/vulnerability-testing-patterns.md line 17. Read 2026-10-05, commit f425adc.

    SKILL.md, line 6 ↗reference/api-dast.md, line 24 ↗reference/mobile-dast.md, line 94 ↗reference/nuclei-templates.md, line 54 ↗reference/vulnerability-testing-patterns.md, line 17 ↗reference/vulnerability-testing-patterns.md, line 17 ↗
  • No serious risk pattern found

    Launch7’s automated check read all 14 text files in this skill and matched none of its serious risk patterns. This is not a guarantee: a check like this can miss new or disguised tricks, and the author can change the files after the check.

    How we know

    Read 2026-10-05, commit f425adc by pipeline/trust/analyze.py — 40+ patterns for hidden text, prompt injection, downloads that run, credential access and more. It reads; it never runs the skill.

  • Recently maintained

    Its repository has had changes recently.

    How we know

    Last push to simota/agent-skills: 2026-09-18 (17 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.

  1. Built in your browser from the SKILL.md on GitHub — nothing passes through Launch7.

  2. In Claude, open Customize → Skills, press +, then Create skill → Upload a skill, and choose the .zip.

  3. Make sure code execution is switched on (Settings → Capabilities). Skills need it.

  4. 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 simota

All from this publisher →
  • accord

    Authoring unified specification packages across Business/Development/Design teams via staged elaboration (L0 Vision, L1 Requirements, L2 Team Detail, L3…

    simotaInstructions only
  • anvil

    Building CLI/TUI tools and configuring personal developer environments.

    simotaInstalls other software
  • artisan

    Implementing production frontend code for React/Vue/Svelte: hooks design, state management, Server Components, form handling, data fetching.

    simotaInstructions only
  • attest

    Verifying spec compliance: extracts ACs from specs, adversarially checks conformance, generates BDD scenarios and traceability matrices.

    simotaInstructions only
  • bazaar

    Orchestrating super-premium landing-page pipelines (Discover to Launch) across 6 craft axes with rubrics and quality gates.

    simotaInstructions only