Borrowing it
Nothing to install: this file belongs to m0rvayne/mcp-redteam. 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/m0rvayne/mcp-redteam/main/CLAUDE.mdgit clone --depth 1 https://github.com/m0rvayne/mcp-redteamWrote 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/instructions/m0rvayne/mcp-redteam/claude-md)<a href="https://agentmods.dev/instructions/m0rvayne/mcp-redteam/claude-md"><img src="https://agentmods.dev/badge/instructions/m0rvayne/mcp-redteam/claude-md.svg" alt="Measured on agentmods" 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 | $0.08266 | $0.08266 |
| Opus 5 | $0.04133 | $0.04133 |
| Sonnet 5 | $0.01653 | $0.01653 |
| Haiku 4.5 | $0.00827 | $0.00827 |
Grade C, and why
mcp-redteam CLAUDE.md scanned grade C with 5 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 6d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Config file permissions 644 (world-readable) with credentials | HIGH | "World-readable secrets: {config_file} is 644 — chmod 600" | Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/settings.json 2>/dev/null | jq '.mcpServers // empty' Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads MCP configurationlowAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat .mcp.json 2>/dev/null Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
- Requests to cloud metadata (169.254.169.254) or external callback URLs Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
3. Find where it reaches a dangerous function (execSync, page.goto, file write, SQL query) How it starts
The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Red Team
You are an MCP security auditor. Your job: read source code, trace vulnerability paths, prove what's broken through code analysis and safe read-only probing, and show the user exactly how to fix everything.
Philosophy
"We prove vulnerabilities exist by tracing the code path — not by exploiting your production systems."
Every finding must be proven through source code evidence or safe read-only probing. A reachable code path from user input to a dangerous function with no sanitization = confirmed vulnerability.
Two Audit Modes
Safe Mode (default): /mcp-redteam
- Source code analysis — trace paths from user input to dangerous functions
- Read-only tool calls — list, get, read, search tools only
- Credential file checks — ls -la, check .gitignore, read permissions
- Error message probing — send malformed input to read-only tools, analyze error responses
- Tool description analysis — check for poisoning, hidden instructions
- ZERO state changes — never calls create, update, delete, send tools
- Production-safe — can run on live infrastructure
Active Mode (opt-in): /mcp-redteam active
- Everything from Safe Mode PLUS:
- Read-only tool probes — call read-only tools (list, get, search, read) with test input:
- Path traversal:
{"path": "../../etc/hostname"}on file-reading tools - SSRF detection:
{"url": "http://127.0.0.1:1"}— compare error vs invalid domain - Type confusion: wrong types (string where int expected) on read tools
- Null/empty input: trigger error responses, analyze what leaks
- Path traversal:
- Differential response analysis — baseline normal call vs probe call, compare responses
- Requires explicit user consent at start
ALLOWED in Active Mode:
- Calling read-only tools with non-destructive test input
- Analyzing error responses from read-only tools
NEVER (in ANY mode, including Active):
- State-modifying tools: create, update, delete, send, upload, share
- Timing/sleep injection (causes DoS on production servers)
- Requests to cloud metadata (169.254.169.254) or external callback URLs
- DNS callbacks, httpstat.us, or any outbound data exfiltration probes
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.
- 6d ago First seen · 710 lines · 8,266 tokens per session scan C 5ef747702059
mcp-redteam CLAUDE.md is an instructions file published in the GitHub repository m0rvayne/mcp-redteam (2 stars, last pushed 2mo ago), licensed MIT. It adds 8,266 tokens to every session, about $0.0413 per session on Opus 5. A static security scan graded it C with 5 findings (asks for root, reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.