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 skills/fb0sh/pentester/ai-mcp-securitynpx skills add fb0sh/pentester --skill ai-mcp-securitygit clone --depth 1 https://github.com/fb0sh/pentesterWrote 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/skills/fb0sh/pentester/ai-mcp-security)<a href="https://agentmods.dev/skills/fb0sh/pentester/ai-mcp-security"><img src="https://agentmods.dev/badge/skills/fb0sh/pentester/ai-mcp-security.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00046 | $0.00749 |
| Opus 5 | $0.00023 | $0.00375 |
| Sonnet 5 | $0.00009 | $0.00150 |
| Haiku 4.5 | $0.00005 | $0.00075 |
Grade A, and why
ai-mcp-security 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 5d 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.
This is a copy
100% identical to ai-mcp-security — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
AI 与 MCP 安全评估 Skill
当目标包含 LLM、Agent、MCP 工具、Skills、RAG、Memory、Plugin 或模型服务组件时使用本 Skill。
前置条件：如果 AI 表面只是展示层，真正的阻塞仍是客户端签名或加密协议，先回到 client-reverse Skill。
场景路由
| 风险类型 | 首选参考 |
|---|---|
| Prompt 注入 / 间接注入 / CoT 干扰 | references/ai-app-security.md |
| 工具滥用 / MCP 投毒 / Skills 供应链 | references/04-ai-and-mcp-security-integrated.md MCP 章节 |
| 权限逃逸 / 角色越界 / 凭据滥用 | references/ai-identity-security.md |
| 数据泄露 / Prompt 泄漏 / 模型逆推 | references/ai-data-security.md |
| 容器逃逸 / CI-CD / 沙箱失败 | references/ai-baseline-security.md |
| 模型风险 / 对抗样本 / 后门 | references/ai-model-security.md |
| 影响分类与覆盖评估 | references/gaarm-risk-matrix.md |
测试流程
1. 应用层攻击
- 直接 Prompt 注入
- 间接注入（通过外部数据源）
- CoT 干扰与指令覆盖
- Agent 滥用（未授权操作）
- 代码执行突破
- Memory 投毒
2. MCP 与 Agent 风险
- 工具描述投毒
- 指令覆盖
- 隐藏指令注入
- 未授权资源访问
- Skills/Rules 供应链问题
3. 身份与授权
- 动作滥用
- 角色逃逸
- 权限漂移
- 云凭据滥用
4. 数据与隐私
- Prompt 泄漏
- 敏感数据暴露
- 训练数据问题
- 模型逆推
- API 数据窃取
5. 基线与部署
- CI/CD 缺陷
- 容器逃逸
- 向量数据库安全
- 沙箱失效
- 环境隔离缺陷
- 模型服务缺陷
参考文档
references/04-ai-and-mcp-security-integrated.md— AI 与 MCP 安全整合参考references/ai-app-security.md— AI 应用安全references/ai-identity-security.md— AI 身份安全references/ai-data-security.md— AI 数据安全references/ai-baseline-security.md— AI 基线安全references/ai-model-security.md— AI 模型安全references/gaarm-risk-matrix.md— GAARM 风险矩阵
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 76 lines · 46 tokens per session scan A 3e27bdd15e3b
ai-mcp-security is a skill published in the GitHub repository fb0sh/pentester (23 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 749 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to ai-mcp-security, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
transilience-report-style
Threat Intelligence Report Design System — ReportLab-based PDF generation for A4 reports with Transilience branding, typography, and layout standards.
firewall-review
Evidence-safe firewall ruleset audit reference specification — 22 documented detector patterns (17 vendor-agnostic plus 5 FortiGate-specific), a 15-check semantic catalogue, CIS Fortinet FortiGate Benchmark guidance, a custom customer-policy benchmark, and consolidated network-team Excel profiles including grouped…
pentest-engagement
Run a professional penetration engagement OR a network vulnerability scan from a scope. WEB mode (apex domains / app URLs) — mandatory surface expansion, systematic OWASP attack-class coverage, reversible active exploitation, authoritative validation, Transilience PDF. NETWORK mode (a list of IPs/CIDRs, e.g. 1500…
attack-path-stitcher
Stitches confirmed single-asset findings into multi-hop attack paths across the organization. Builds a graph where nodes are assets and edges are confirmed exploit hops citing the findings that enable them.
coordination
Pentest coordination — orchestrates executor and validator agents with context-controlled spawning. Entry point for all engagements.
dfir
Digital forensics and incident response - Windows event log analysis, PCAP forensics, filesystem artifact analysis, AD attack detection, and timeline correlation. Use when investigating security incidents, analyzing Sherlocks, or performing threat hunting on provided evidence files.