mcpnuke: Skill for Cursor

.cursor/skills/mcpnuke-extend-dvmcp/SKILL.md

mcpnuke-extend-dvmcp is a skill for Cursor from babywyrm/mcpnuke. It costs 46 tokens per session (830 once invoked), scanned A, original, MIT.

A testing workflow for adding new security-challenge test classes to the mcpnuke test suite. DVMCP challenges are tests for weaknesses in systems that connect language models to tools and data.

In plain words
What is it for?
Use it when adding coverage for a new issue such as prompt injection, tool poisoning, permission errors, token theft, code execution, remote access, or supply-chain risks.
Why use it?
It gives new challenge tests the same structure as the existing suite. This makes positive cases, negative cases, severity checks, pipeline tests, and optional live tests easier to verify.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is babywyrm/mcpnuke's own configuration. It tells Cursor how to work on mcpnuke itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcpnuke configures →

Reuse

Borrowing it

Nothing to install: this file belongs to babywyrm/mcpnuke. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/babywyrm/mcpnuke/main/.cursor/skills/mcpnuke-extend-dvmcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/babywyrm/mcpnuke

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcpnuke-extend-dvmcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp/github.svg)](https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp)
Your own site
<a href="https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp"><img src="https://agentmods.dev/badge/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcpnuke-extend-dvmcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp"><img src="https://agentmods.dev/badge/skills/babywyrm/mcpnuke/mcpnuke-extend-dvmcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.00830
Opus 5 $0.00023 $0.00415
Sonnet 5 $0.00009 $0.00166
Haiku 4.5 $0.00005 $0.00083

Measured 11d ago against content hash 2b5967511106, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

mcpnuke-extend-dvmcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/skills/mcpnuke-extend-dvmcp/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extend mcpnuke DVMCP Tests

Test File

All DVMCP tests live in tests/test_dvmcp.py.

Existing Structure

# Helpers
def _make(tools, url=..., resources=None, prompts=None) -> TargetResult
def _checks_found(result) -> set[str]
def _severities(result) -> set[str]

# Per-challenge classes
class TestDVMCPChallenge1PromptInjection:     # Ch1, port 9001
class TestDVMCPChallenge2ToolPoisoning:        # Ch2, port 9002
class TestDVMCPChallenge3Permissions:          # Ch3, port 9003
class TestDVMCPChallenge4RugPull:              # Ch4, port 9004
class TestDVMCPChallenge5TokenTheft:           # Ch5, port 9005
class TestDVMCPChallenge6CodeExecution:        # Ch6, port 9006
class TestDVMCPChallenge7RemoteAccess:         # Ch7, port 9007
class TestDVMCPChallenge8RateLimitAndLeakage:  # Ch8, port 9008
class TestDVMCPChallenge9SupplyChain:          # Ch9, port 9009
class TestDVMCPChallenge10MultiVector:         # Ch10, port 9010

# Pipeline integration
class TestDVMCPFullPipeline:

# Live tests (skipped by default)
class TestDVMCPLive:

Adding a New Challenge Class

Template

class TestDVMCPChallengeNYourCheck:
    """DVMCP Challenge N: description."""

    def test_positive_case(self):
        """Tool with vuln pattern should be flagged."""
        r = _make([{
            "name": "vuln_tool",
            "description": "Description containing vulnerable pattern",
            "inputSchema": {"properties": {}},
        }])
        check_your_check(r)
        assert "your_check" in _checks_found(r)
        assert "EXPECTED_SEVERITY" in _severities(r)

    def test_variant(self):
        """Different variant of the same vuln class."""
        r = _make([{
            "name": "another_tool",
            "description": "Different trigger pattern",
            "inputSchema": {"properties": {"param": {"type": "string"}}},
        }])
        check_your_check(r)
        assert "your_check" in _checks_found(r)

    def test_clean_tool_not_flagged(self):
        """Clean tool should not trigger this check."""
        r = _make([{
            "name": "safe_tool",
            "description": "Completely benign tool",
            "inputSchema": {"properties": {}},
        }])
        check_your_check(r)
        assert "your_check" not in _checks_found(r)

Read the full file on GitHub · 103 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 103 lines · 46 tokens per session scan A 2b5967511106

Subscribe to this mod's changes

mcpnuke-extend-dvmcp is a skill published in the GitHub repository babywyrm/mcpnuke (2 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 830 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

AI & LLM Security

LLM and AI application security testing — prompt injection, jailbreak resistance, OWASP LLM Top 10 (2025), RAG and agent/tool-use security, model supply chain, and AI red teaming for authorized assessments.

Masriyan/Claude-Code-CyberSecurity-Skill · 50 tokens

prompt-injection-tester

Red-team an LLM application against prompt injection and jailbreaks using a curated, categorized payload library and canary-based detection, then produce a resilience score. Use when the user asks to "test my chatbot for prompt injection", "check if my AI app is jailbreakable", "red-team my LLM", "evaluate…

NovaCode37/claude-security-skills · 84 tokens

dast-config

Reviews DAST tool configurations against OWASP Top 10:2021 and OWASP Testing Guide v4.2. Auto-invoked when reviewing OWASP ZAP configurations, DAST CI/CD integration, scan policies, or authenticated scanning setups. Produces a DAST maturity assessment covering scan policy configuration, active vs passive scanning, API…

UnitOneAI/SecuritySkills · 83 tokens

testing-agents-for-indirect-prompt-injection

Test whether an AI agent obeys instructions hidden in the content it ingests, rather than only the user's. Enumerate every channel through which untrusted content reaches the model context (retrieved docs, fetched pages, uploaded files, emails, tool outputs, filenames, images and PDFs, other agents), plant…

UnboundCompute/security-agent-skills · 127 tokens

api-31-idor

IDOR (Insecure Direct Object Reference) testing checklist: object ID enumeration, horizontal/vertical privilege escalation, GUID predictability, indirect references via hashes, chained IDOR, and API endpoint IDOR. Use for web app pentests and bug bounty IDOR discovery.

vigilantshield/Claude-HunterKit · 60 tokens

api-22-business-logic

Business logic vulnerability testing for web/mobile/API engagements. Covers workflow bypass, state machine violations, multi-step process abuse, price/quantity/discount manipulation, currency confusion, coupon stacking, refund/chargeback abuse, race conditions on logic boundaries, parameter tampering for hidden flows…

vigilantshield/Claude-HunterKit · 136 tokens