接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y [email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add agent-crashtest -- npx -y agent-crashtest@0.5.1在終端機中執行。
{ "mcpServers": { "agent-crashtest": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
Security for AI agents in your CI.
Claude Code, Codex and other coding agents now run in GitHub Actions on issues, PR comments and fork PRs, with your API keys and a write token in the environment. One wrong line in the workflow, and anyone on GitHub can open an issue that tells your agent what to do.
agent-crashtest finds those workflows and blocks them in review, before they reach main.
# .github/workflows/agent-crashtest.yml
name: agent-crashtest
on: [pull_request]
permissions:
contents: read
jobs:
scan:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: glibey/agent-crashtest@v1
Findings show up as annotations on the PR diff and as a table in the job summary, and the check fails on high or worse.
on:
issues:
types: [opened] # anyone on GitHub can open an issue
jobs:
triage:
runs-on: ubuntu-latest
steps:
- uses: anthropics/claude-code-action@v1
with:
anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
allowed_non_write_users: "*" # turns off the write-access check
claude_args: --allowedTools "Bash,Read" # any shell command
CRITICAL Anyone on GitHub can drive the agent in .github/workflows/triage.yml
CRITICAL Agent may run any shell command in .github/workflows/triage.yml
The issue text becomes the agent's instructions, and the agent can run any command next to your secrets.
Narrow the tools to what the job needs (--allowedTools "Bash(gh issue edit:*),Read") and it drops to the
low-risk setup the action's own security docs recommend.
It understands the guards people actually use, so it doesn't cry wolf: author_association and role allowlists,
gate jobs, maintainer-only labels, merged-PR-only triggers, and schedule-only workflows.
The same scanner checks the agent on your machine: Claude Code, Codex, Cursor, MCP servers and instruction files.
npx agent-crashtest # scan this project and your global agent config
npx agent-crashtest --fix # apply the safe fixes, each shown as a diff first
--fix changes only what has one right answer: it denies agent reads of secret files, pins npx MCP servers to
the current version, and removes enableAllProjectMcpServers and skipDangerousModePermissionPrompt. Files in your
home directory are asked about separately and never changed with --yes.
Let the agent scan, explain each finding for your project, and fix it one change at a time with your OK.
/plugin install agent-crashtest --marketplace glibey/agent-crashtestnpx skills add glibey/agent-crashtestscan tool):{
"mcpServers": {
"agent-crashtest": { "command": "npx", "args": ["-y", "[email protected]", "mcp"] }
}
}
For Codex, in ~/.codex/config.toml:
[mcp_servers.agent-crashtest]
command = "npx"
args = ["-y", "[email protected]", "mcp"]
Running AI agents in CI across an organization? We're building a Team version:
👉 Join the early access list, free during the beta.
A security check that cries wolf gets removed from CI. The rules were run against thousands of public repositories
that run AI agents in GitHub Actions or commit agent config, and every critical finding was reviewed by hand.
Patterns that turned out safe, such as allowlist-gated and schedule-only workflows, Bash(npx eslint:*),
curl localhost and defensive rules in CLAUDE.md, are regression tests now.
Found a false positive or a missed risk? Open an issue.
.env files are read for variable names only.npx agent-crashtest --badge
prints a snapshot badge with your grade. For one that stays current, use the workflow badge of the Action; the job summary prints the exact Markdown.
npx agent-crashtest [options]
npx agent-crashtest mcp run as an MCP server over stdio
--dir <path> project to scan (default: current directory)
--project-only skip global config in your home directory
--fix show safe fixes as diffs and apply them after you confirm
--yes with --fix: apply project changes without asking (never touches files in ~)
--badge print a README badge with your grade
--json machine-readable output
--fail-on <level> exit 1 on findings at or above: critical, high, medium, low
--ci same as --fail-on high
--github GitHub Actions mode: PR annotations, job summary, step outputs
--demo scan a deliberately vulnerable sample project
Action inputs: path (default .), fail-on (default high). Outputs: score, grade, critical, high.
.agent-crashtest.yml): declare which workflows may run agents, with which tools, enforced in CI--fix for CI workflows: narrow tools and drop outsider access in agent workflowsIdeas and requests: open an issue.
MIT
Crash-test your AI coding agent setup. One command, zero config: find out how easily Claude Code, Cursor & MCP can be hijacked by prompt injection.
{ "mcpServers": { "agent-crashtest": { "command": "npx", "args": [ "-y", "[email protected]" ] } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
這筆記錄未列出必要的環境變數。
Agent Crashtest 透過 stdio 在本機執行。
上次檢查時間:2026-11-15。 Crash-test your AI coding agent setup. One command, zero config: find out how easily Claude Code, Cursor & MCP can be hijacked by prompt injection.