DSH PluginsSkill
skills
anthropics
Public repository for Agent Skills
Structure check pending
agent-skills
Back to Marketplace
DSH PluginsSkill
VulnClaw
Netw0rkNoob/VulnClaw
VulnClaw is a tool for DeepSeek Harness. Built on AI Agent + MCP toolchain + pentest Skill orchestration, with an LLM: natural language input → fully automated 'information gathering → vulnerability discovery → exploitation → report generation' workflow.
- Stars
- 3.3k
- Forks
- 447
- Issues
- 19
- Update
- 55 days
REVIEW SCORECARD
Review Scorecard
8.2/10Good
License compliance9.0
Engineering quality9.0
Content completeness7.0
Repository scale7.0
Maintenance activity8.0
✓ No risk detected · Automated scan results are for reference only, not an official endorsement
AI DEEP REVIEW
Worth AI Review
7.2/10Cautious
Powerful AI-driven pentest agent with strong docs, but offensive tooling and shell/code execution warrant authorized-use
Code quality7
README shows codecov badge, PyPI packaging, Docker support, and modular MCP/plugin architecture, but no visible test suite or CI config details beyond the coverage badge.
Security5
Ships a shell_command tool, python_execute (self-described as 'high-risk experimental, not a strong sandbox'), and TLS verification disabled by default for CTF targets, which are meaningful risks despite the authorized-only scope disclaimer.
Utility8
Automates the full recon-to-report pentest workflow with 14 LLM providers, 50 skills, and MCP tooling, addressing a real and popular security testing pain point.
Maintenance8
Last updated 2026-09-05, not archived, with active versioning (v0.3.8), Discord community, and a project website indicating ongoing development.
Documentation8
README provides install commands, four-step quickstart, Docker instructions, architecture overview, and feature list, though some sections (e.g. config step 2) appear truncated.
Generated by AI after reading the project README — a decision aid, not an endorsement. Neutral scores are given when information is limited.
PROJECT READMEREADMEExpandCollapse
Loading GitHub README...
The GitHub README is temporarily unavailable. Please try again later.
Open repositoryINSTALL REFERENCE
Install reference
pip install vulnclawThis command was extracted from an explicit README install reference and is display-only; the DSH host will not execute it automatically.
PROJECT TOPICS
Project topics
VALIDATION LADDER
Validation progress
01Store discoveryPassed
02ClassificationPassed
03Structure checkPending
04Sandbox validationPending
FAQ
Frequently Asked Questions
What is VulnClaw used for?
Built on AI Agent + MCP toolchain + pentest Skill orchestration, with an LLM: natural language input → fully automated 'information gathering → vulnerability discovery → exploitation → report generation' workflow.
How popular is VulnClaw?
VulnClaw has 3,311 stars and 447 forks on GitHub, last updated 2026-09-05.
What license does VulnClaw use?
VulnClaw is distributed under the MIT license.
Is VulnClaw compatible with DeepSeek Harness?
VulnClaw is listed in the DSH Universe directory as a tool for DeepSeek Harness. This plugin is listed in the DSH Universe directory and covered by its validation pipeline.
CLASSIFICATION EVIDENCE
Classification evidence
Project typeSkill
Feature categoryDSH Plugins
Rule confidenceHigh
The system checks GitHub Topics against the site taxonomy and keyword rules. Current matches:skill。
DSH PluginsSkill
cc-switch
farion1231
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
Structure check pending
ai-toolsclaude-codecodexdeepseek-harness
DSH PluginsSkill
graphify
Graphify-Labs
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Structure check pending
ai-agentsantigravityastclaude-code
DSH PluginsSkill
caveman
JuliusBrussee
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
Structure check pending
aianthropiccavemanclaude
DSH PluginsSkill
taste-skill
Leonxlnx
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Structure check pending
agentaiclaudeclaude-code
DSH PluginsSkill
awesome-claude-skills
ComposioHQ
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Structure check pending
agent-skillsai-agentsantigravityautomation