aishield-security-scan

aishield-security-scan is a skill for Claude Code, Codex from lm203688/aishield. It costs 91 tokens per session (995 once invoked), scanned A, original, MIT.

A security scanner for MCP servers, agent configurations, and AI skills. It checks for risks such as tool poisoning, memory poisoning, excessive permissions, and sandbox escape, and can produce SBOM and SARIF reports.

In plain words
What is it for?
Auditing remote repositories, scanning a local agent workspace, exporting results for code-scanning systems, and checking MCP or skill security risks.
Why use it?
It helps identify unsafe instructions or configuration before an agent starts or a server is deployed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/scan_workspace.py /path/to/workspace --md.

Good fit Auditing remote repositories, scanning a local agent workspace, exporting results for code-scanning systems, and checking MCP or skill security risks.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/lm203688/aishield
agentmods
npx agentmods add skills/lm203688/aishield/claude-skill

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for aishield-security-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/lm203688/aishield/claude-skill.svg)](https://agentmods.dev/skills/lm203688/aishield/claude-skill)
Your own site
<a href="https://agentmods.dev/skills/lm203688/aishield/claude-skill"><img src="https://agentmods.dev/badge/skills/lm203688/aishield/claude-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 995 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00091 $0.00995
Opus 5 $0.00046 $0.00498
Sonnet 5 $0.00018 $0.00199
Haiku 4.5 $0.00009 $0.00100

Measured 7d ago against content hash 944dd73894f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aishield-security-scan scanned grade A with 1 finding 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 7d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "$AISHIELD_API/api/v1/audit" \
distribution/claude-skill/SKILL.md · 77 lines

What it actually says

AIShield Security Scan

你帮助用户评估 MCP 服务器、AI Skill 与 Agent 工作区的安全性。AIShield 是本地、开源、零成本的扫描器,覆盖 OWASP MCP Top 10 + OWASP Agentic AI Top 10 + 沙箱硬化,共 214 条 MCP 规则 / 220 条 Skill 规则,输出 CycloneDX SBOM 与 SARIF。

核心不变量:扫描过程绝不执行被扫配置里的任何命令。 很多同类工具为了读取 tools/list 会真实启动被扫服务——那等于先中招再体检。

何时使用

  • 用户想审计一个 GitHub 上的 MCP 服务器或 Agent 仓库
  • 用户担心工具投毒、提示注入、记忆投毒、过度代理、沙箱逃逸
  • 用户要在 agent 沙箱启动前预扫工作区里的 MCP 配置与 skill
  • 用户需要 SBOM / SARIF 接入 CI
  • 用户想给自己的 Agent 申请 AIShield 安全认证证书

如何执行

先约定端点,不要在命令里写死内网地址:

# 自托管时指向你自己的实例;不设置则用官方托管端点
AISHIELD_API="${AISHIELD_API:-https://aishield.tools}"

方式 A:扫远程仓库

curl -X POST "$AISHIELD_API/api/v1/audit" \
  -H 'Content-Type: application/json' \
  -d '{"source_url":"https://github.com/owner/repo","tool_type":"mcp"}'

tool_typemcp(MCP 服务器)或 skill(AI Skill / 提示词资产)。

方式 B:agent 工作区启动前预扫(纯本地,不联网)

python scripts/scan_workspace.py /path/to/workspace --md

解析工作区里的 .mcp.json、forge / Goose / Open Interpreter 配置与 skill 文件, 只读判定,产出可核对的风险表。适合在 sandbox 拉起 agent 之前跑。

方式 C:导出 SARIF 接 Code Scanning

curl -X POST "$AISHIELD_API/api/v1/export/sarif" \
  -H 'Content-Type: application/json' \
  -d '{"scan_result": <上一步返回> }'

方式 D:查他人 Agent 的信任分

curl "$AISHIELD_API/api/v1/trust/score/agent-f864141ae08f"
curl "$AISHIELD_API/api/v1/registry"

输出解读

  • overall_score / risk_level:整体安全评分与风险等级
  • owasp_coverage / agentic_coverage:命中的 MCP / Agentic 类别
  • score_breakdown / top_deductions:分数是怎么扣的,逐项可追
  • sbom:CycloneDX 供应链清单;sarif:可进 CI 的发现项
  • 评分 ≥80 自动签发认证证书(certification 字段)

注意事项

  • Markdown 不等于文档:对 skill 类资产,SKILL.md 本身就是可执行载荷,AIShield 不会把其中的危险模式当"文档示例"降级处理。
  • 语义分析为可选层:配置远程 LLM 需设置 AISHIELD_LLM_URLAISHIELD_LLM_KEY;不设置则只跑规则引擎。
  • 隔离与内容安全是两件事:容器 / 微 VM 沙箱管住"能做什么",AIShield 管住"读进来的东西该不该信"。两者互补。
  • 报告与基准见 https://aishield.toolsdocs/agent-security-benchmark-2026.md
Changes

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.

  1. 7d ago First seen · 77 lines · 91 tokens per session scan A 944dd73894f9

Subscribe to this mod's changes

aishield-security-scan is a skill published in the GitHub repository lm203688/aishield (2 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 995 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

polygraph

Behavioral trust grades (A–F) for MCP servers. Use when an agent needs to check whether an MCP server is safe before using it, verify an onchain attestation before trusting or paying a server, look up a server's published grade, get a project graded, or understand why a server received a grade. Polygraph connects to…

polygraphso/litmus · 225 tokens

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

specflow-use

To connect Rosetta with Grid Dynamics SpecFlow MCP; only when SpecFlow is mentioned and the MCP is installed.

griddynamics/rosetta · 27 tokens

opik-diagnose

Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…

comet-ml/opik-mcp · 147 tokens

ue-mcp-epic-routing

Use when deciding between ue-mcp's native category actions and Epic's wrapped ToolsetRegistry tools (the epic actions, incl. the Blueprint graph DSL) for a task in Unreal. Pulls in when authoring Blueprint graph bodies, or any time both a native action and an epic action could do the job and you need to pick.

db-lyon/ue-mcp · 81 tokens

mcp-google-map-project

Project knowledge for developing and maintaining @cablate/mcp-google-map. Architecture, Google Maps API guide, GIS domain knowledge, and design decisions. Read this skill to onboard onto the project or make informed development decisions.

cablate/mcp-google-map · 49 tokens