Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add mcp/headyzhang/agent-audit/vuln-shellgit clone --depth 1 https://github.com/HeadyZhang/agent-auditWrote 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/mcp/headyzhang/agent-audit/vuln-shell)<a href="https://agentmods.dev/mcp/headyzhang/agent-audit/vuln-shell"><img src="https://agentmods.dev/badge/mcp/headyzhang/agent-audit/vuln-shell.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
shell 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 4d 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.
What it actually says
{
"shell": {
"command": "npx",
"args": [
"-y",
"mcp-shell-server"
],
"alwaysAllow": [
"run_command",
"run_background"
]
}
}What else claude_desktop_config.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 4d ago First seen · 13 lines scan A d903ad61a775
shell is an MCP server published in the GitHub repository HeadyZhang/agent-audit (225 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
mcp-zap-server
MCP server "mcp-zap-server" as configured in dtkmn/mcp-zap-server. Runs in Docker (ghcr.io/dtkmn/mcp-zap-server:v0.8.0). Needs 8 environment variables to run.
docs
MCP server "docs", hosted remotely at docs.example.com, as configured in meghal86/promptsonar.
mcp-tenant-isolation
Static analysis scanner for MCP server code and multi-tenant SaaS applications. Runs locally from the mcp-tenant-isolation npm package.
blindoracle
MCP server "blindoracle", hosted remotely at craigmbrown.com, as configured in craigmbrown/blindoracle-mcp.
owasp
MCP server "owasp", hosted remotely at gateway.pipeworx.io, as configured in pipeworx-io/mcp-owasp.
provekit-mcp
MCP server "provekit-mcp" as configured in Th3Circle-app/provekit-mcp. Runs locally from the provekit-mcp Python package.