ToolTrust
C27/100
bojieli

ai-agent-book

mcp1.2

@bojieli

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

By bojieli | 41 findings | Scanned 7/28/2026 | tooltrust-scanner/v0.3.19 | 22.8k

1 Critical7 Low33 Info

Risk Summary

Needs Approval

Excessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (41)

  • CriticalAS-006

    💻Arbitrary Code Execution

    heuristic signal

    Bash:tool name or description implies arbitrary script/code execution (evaluate_script, execute javascript, etc.)

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×7

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    TaskBashWebFetchTodoWriteWebSearchBashOutputKillBash

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-002

    ⚠️Excessive Permissions ×16

    declared capabilities: code/command execution, network access, filesystem access

    TaskBash

    declared capabilities: filesystem access

    GlobGrepLSExitPlanModeReadEditMultiEditWriteNotebookEdit

    declared capabilities: network access, filesystem access, HTTP requests

    WebFetch

    declared capabilities: code/command execution, network access, filesystem access, database access

    TodoWrite

    declared capabilities: network access, database access, HTTP requests

    WebSearch

    declared capabilities: code/command execution

    BashOutputKillBash

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×16

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    TaskBashGlobGrepLSExitPlanModeReadEditMultiEditWriteNotebookEditWebFetchTodoWriteWebSearchBashOutputKillBash

    Fix: Review and remediate the identified issue.

  • InfoAS-006

    💻Arbitrary Code Execution

    Grep:tool name or description implies arbitrary script/code execution — capability unconfirmed (no exec permission or code/script/eval input property found)

    Fix: This tool can execute arbitrary code or shell commands on the host system. Remove it unless strictly required. If kept: (1) restrict access to trusted users/agents only, (2) require human approval before each invocation (Claude Desktop: set approval_required: true; other clients: enable equivalent confirmation), (3) use the most restrictive sandbox or read-only mode available, and (4) never expose this tool to untrusted input sources.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y ai-agent-book"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade C](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-c.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)