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.
curl -O https://raw.githubusercontent.com/babywyrm/mcpnuke/main/.cursor/skills/mcpnuke-run-tests/SKILL.mdgit clone --depth 1 https://github.com/babywyrm/mcpnukeWrote 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.
[](https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-run-tests)<a href="https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-run-tests"><img src="https://agentmods.dev/badge/skills/babywyrm/mcpnuke/mcpnuke-run-tests/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.
<a href="https://agentmods.dev/skills/babywyrm/mcpnuke/mcpnuke-run-tests"><img src="https://agentmods.dev/badge/skills/babywyrm/mcpnuke/mcpnuke-run-tests.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00816 |
| Opus 5 | $0.00020 | $0.00408 |
| Sonnet 5 | $0.00008 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
mcpnuke-run-tests 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.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run mcpnuke Tests
Quick Reference
All commands use uv run — no venv activation needed.
# Full suite
uv run pytest tests/ -v
# Specific test file
uv run pytest tests/test_dvmcp.py -v
# Specific test class
uv run pytest tests/test_dvmcp.py::TestDVMCPChallenge1PromptInjection -v
# Specific test
uv run pytest tests/test_dvmcp.py::TestDVMCPChallenge1PromptInjection::test_ignore_instructions_payload -v
# Stop on first failure
uv run pytest tests/ -v -x
# With output capture disabled (see print statements)
uv run pytest tests/ -v -s
Test Categories
| File | What it tests | Needs network? |
|---|---|---|
test_dvmcp.py |
All 10 DVMCP challenges (offline) | No |
test_dvmcp.py::TestDVMCPLive |
Live DVMCP servers | Yes (DVMCP_LIVE=1) |
test_cli.py |
CLI argument parsing | No |
test_diff.py |
Differential scanning | No |
test_patterns.py |
Regex pattern matching | No |
test_rate_limit.py |
Rate limit check | No |
test_prompt_leakage.py |
Prompt leakage check | No |
test_supply_chain.py |
Supply chain check | No |
test_checks_integration.py |
Cross-check integration | No |
test_k8s.py |
K8s checks and discovery | No |
test_fast_sampling.py |
Tool scoring and sampling | No |
test_webhook_persistence.py |
Webhook persistence check | No |
test_response_credentials.py |
Response credential check | No |
test_exfil_flow.py |
Exfil flow check | No |
test_config_tampering.py |
Config tampering check | No |
test_credential_in_schema.py |
Schema credential check | No |
test_ssrf_probe.py |
SSRF probe check | No |
test_actuator_probe.py |
Actuator probe check | No |
test_public_targets.py |
Live public MCP servers | Yes (MCP_PUBLIC_TARGETS=1) |
Interpreting Failures
Import errors
Package not installed. Fix:
cd ~/mcpnuke && uv sync --all-extras
# Or just re-run quickstart:
./quickstart.sh --skip-tests
Assertion errors in checks
A check isn't finding what it should. Look at:
- The pattern in
patterns/rules.py— does it match the test input? - The check function — is it scanning the right fields?
- The test data — does the tool description actually contain the pattern?
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.
- 11d ago First seen · 92 lines · 41 tokens per session scan A 5a5e18fb2710
mcpnuke-run-tests is a skill published in the GitHub repository babywyrm/mcpnuke (2 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 816 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.
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.
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…
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…
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…
eval-threat-model
Developer/test skill that grades the SEMANTIC quality of a produced threat model (plausibility, severity proportionality, STRIDE coverage, mitigation actionability, missed surfaces) via a find→adversarial-verify loop over a frozen run. Complements the structural pytest/qachecks suite; does NOT re-run the pipeline.
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.