← 返回 Skills 市场
733
总下载
0
收藏
1
当前安装
36
版本数
在 OpenClaw 中安装
/install agent-bom-scan
功能描述
Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust for package CVEs (OSV, NVD, EPSS, KEV), container...
使用说明 (SKILL.md)
agent-bom-scan — AI Supply Chain Vulnerability Scanner
Checks packages for CVEs, scans container images natively, verifies package provenance via Sigstore, scans filesystems, and generates SBOMs.
Install
pipx install agent-bom
agent-bom agents # discover agents and scan dependencies
agent-bom check langchain==0.1.0 # check a specific package with version
agent-bom image nginx:1.25 # scan container image (native)
agent-bom fs . # scan filesystem packages
agent-bom sbom . # generate SBOM
agent-bom verify agent-bom # verify Sigstore provenance
agent-bom where # show all discovery paths
As an MCP Server
{
"mcpServers": {
"agent-bom": {
"command": "uvx",
"args": ["agent-bom", "mcp", "server"]
}
}
}
When to Use
- "check package" / "is this package safe"
- "scan image" / "scan container"
- "verify" / "check provenance"
- "is this safe" / "CVE lookup"
- "scan dependencies"
- "blast radius"
- "generate SBOM"
Tools (8)
| Tool | Description |
|---|---|
check |
Check a package for CVEs (OSV, NVD, EPSS, KEV) |
scan |
Full discovery + vulnerability scan pipeline |
blast_radius |
Map CVE impact chain across agents, servers, credentials |
remediate |
Prioritized remediation plan for vulnerabilities |
verify |
Package integrity + SLSA provenance check |
diff |
Compare two scan reports (new/resolved/persistent) |
where |
Show MCP client config discovery paths |
inventory |
List discovered agents, servers, packages |
Examples
# Check a package before installing
check(package="langchain", version="0.1.0", ecosystem="pypi")
# Map blast radius of a CVE
blast_radius(cve_id="CVE-2024-21538")
# Full scan
scan()
# Verify package provenance
verify(package="agent-bom")
Guardrails
- Show CVEs even when NVD analysis is pending or severity is
unknown— a CVE ID is still a real finding. - Treat
UNKNOWNseverity as unresolved, not benign — it means data is not yet available. - Do not modify any files, install packages, or change system configuration.
- Only public package names and CVE IDs leave the machine for vulnerability database lookups.
- Ask before scanning paths outside the user's home directory.
Privacy & Data Handling
# Step 1: Install
pip install agent-bom
# Step 2: Review redaction logic BEFORE scanning
# sanitize_env_vars() replaces ALL env var values with ***REDACTED***
# BEFORE any config data is processed or stored:
# https://github.com/msaad00/agent-bom/blob/main/src/agent_bom/security.py#L159
# Step 3: Verify package provenance (Sigstore)
agent-bom verify agent-bom
# Step 4: Only then run scans
agent-bom agents
Verification
- Source: github.com/msaad00/agent-bom (Apache-2.0)
- Sigstore signed:
agent-bom verify [email protected] - 7,100+ tests with CodeQL + OpenSSF Scorecard
- No telemetry: Zero tracking, zero analytics
安全使用建议
This skill appears to be what it says (an on‑host scanner) but it instructs the agent to read many local MCP/agent/project config files that often contain secrets. Before installing: (1) confirm the skill bundle comes from a trusted source (inspect the upstream GitHub repo and the code, especially the sanitize_env_vars implementation referenced in the metadata), (2) run the scanner in an isolated environment or container if possible, (3) avoid running it on machines with sensitive credentials you can't afford to expose, and (4) review any files listed under file_reads to understand what will be accessed. Because this is instruction-only, you should verify the actual agent-bom code (pip package or GitHub source) to confirm the claimed local-only data flow and sanitization behavior.
功能分析
Type: OpenClaw Skill
Name: agent-bom-scan
Version: 0.82.3
The skill requests extensive read access to sensitive configuration files for dozens of AI agents and IDEs (e.g., Claude, Cursor, Windsurf, Snowflake, JetBrains) in SKILL.md. While the stated purpose is to scan these environments for vulnerabilities and the documentation claims to redact credentials locally before processing, the broad access to files known to contain API keys and connection strings represents a high-risk capability. Without the underlying Python source code to verify the redaction logic, the tool's behavior mirrors that of a credential harvester, even though the listed network endpoints (OSV, NVD, GitHub) are legitimate.
能力标签
能力评估
Purpose & Capability
The name/description (agent supply-chain and blast‑radius scanning) align with the things the skill enumerates: package CVE lookups, image scanning, Sigstore verification, and discovery of agent/MCP configuration files. Asking to read MCP and project-level config files is coherent for discovering agents and mapping blast radius.
Instruction Scope
SKILL.md (metadata) explicitly lists many local config paths (~/.config, ~/Library/Application Support, project .mcp.json, etc.) that the skill will read. Those files can contain tokens, credentials, or other sensitive data. The skill claims to sanitize env vars and keep scanning local-first, but because this is an instruction-only skill (no code included in the bundle) the claim cannot be audited here and the instructions grant broad local file read scope.
Install Mechanism
There is no install spec in the bundle (instruction-only). The project recommends installing via pipx/pip or using the project's Docker image; those are standard distribution channels and appropriate for this tool. No arbitrary download URLs are embedded in the skill.
Credentials
The skill declares no required env vars or credentials, which is consistent with its metadata. However it also declares a long list of config files to read — several (Snowflake, Copilot, CLI configs) commonly hold credentials or tokens. That broad local access is disproportionate to an agent skill unless the user explicitly consents and understands what will be read. The sanitization claim helps but cannot be validated from this instruction-only package.
Persistence & Privilege
The skill does not request 'always: true' or persistence. autonomous invocation is listed as restricted in the metadata. It does not ask to change other skills' configs or system-wide settings.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install agent-bom-scan - 安装完成后,直接呼叫该 Skill 的名称或使用
/agent-bom-scan触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.82.3
Release v0.82.3
v0.82.2
Release v0.82.2
v0.81.3
Release v0.81.3
v0.81.1
Release v0.81.1
v0.81.0
Release v0.81.0
v0.80.1
Release v0.80.1
v0.78.1
Release v0.78.1
v0.76.4
Release v0.76.4
v0.76.2
Release v0.76.2
v0.76.1
Release v0.76.1
v0.76.0
Release v0.76.0
v0.75.15
Release v0.75.15
v0.75.14
Release v0.75.14
v0.75.13
Release v0.75.13
v0.75.11
Release v0.75.11
v0.75.10
Release v0.75.10
v0.75.9
Release v0.75.9
v0.75.8
Release v0.75.8
v0.75.7
Release v0.75.7
v0.75.6
Release v0.75.6
元数据
常见问题
agent-bom scan 是什么?
Open security scanner for agentic infrastructure — agents, MCP, packages, blast radius, runtime, and trust for package CVEs (OSV, NVD, EPSS, KEV), container... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 733 次。
如何安装 agent-bom scan?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-bom-scan」即可一键安装,无需额外配置。
agent-bom scan 是免费的吗?
是的,agent-bom scan 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
agent-bom scan 支持哪些平台?
agent-bom scan 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(darwin, linux, windows)。
谁开发了 agent-bom scan?
由 Agent Bom(@msaad00)开发并维护,当前版本 v0.82.3。
推荐 Skills