ai-llm-app-attack

ai-llm-app-attack is a skill for Claude Code, Codex from Ed1s0nZ/CyberStrikeAI. It costs 62 tokens per session (342 once invoked), scanned A, original, Apache-2.0.

A security-testing skill for applications that use artificial-intelligence models, agents, retrieval systems, tool plugins, or model files. It focuses on risks such as prompt injection, unsafe tool use, data poisoning, and dangerous model-file loading.

In plain words
What is it for?
Use it to assess AI chat endpoints, autonomous agents, retrieval-augmented systems, tool or plugin integrations, and model-loading code.
Why use it?
It helps identify ways untrusted instructions or data could make an AI system misuse its tools, expose information, or run unwanted code. It also separates confirmed effects from speculation.

Skill for Claude CodeCodex

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

Good fit Use it to assess AI chat endpoints, autonomous agents, retrieval-augmented systems, tool or plugin integrations, and model-loading code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack
About the project

CyberStrikeAI is a security operations workspace that turns natural-language plans into governed, auditable actions while recording evidence and results for later reuse. Authorized security teams use it to manage agents, tools, vulnerabilities, knowledge, and attack-chain analysis. Catalogue add-ons provide agent and skill workflows for working with the platform.

Ed1s0nZ/CyberStrikeAI · 6,410 stars · on GitHub

Install

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.

Any agent
npx skills add Ed1s0nZ/CyberStrikeAI --skill ai-llm-app-attack
Clone the repo
git clone --depth 1 https://github.com/Ed1s0nZ/CyberStrikeAI

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 ai-llm-app-attack

README.md
[![agentmods](https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack/github.svg)](https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack)
Your own site
<a href="https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack"><img src="https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-llm-app-attack

Your own site · 80×15
<a href="https://agentmods.dev/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack"><img src="https://agentmods.dev/badge/skills/ed1s0nz/cyberstrikeai/ai-llm-app-attack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 342 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 14
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
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 $0.00062 $0.00342
Opus 5 $0.00031 $0.00171
Sonnet 5 $0.00012 $0.00068
Haiku 4.5 $0.00006 $0.00034

Measured 13d ago against content hash 7286e92053f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ai-llm-app-attack 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 13d 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.

skills/ai-llm-app-attack/SKILL.md · 19 lines

What it actually says

AI / LLM 应用攻击

=== AI/LLM应用(大模型应用爆发期真实攻击面) ===
提示注入: 直接(忽略上文输出system prompt) | 间接(更危险):指令藏RAG文档/网页/邮件/工具返回值/图片EXIF → 劫持Agent
🚨Agent工具滥用(最高危,直达RCE): code interpreter→注入执行 | fetch工具→SSRF内网/云元数据 | 文件工具→读/etc/passwd写webshell
  | SQL工具→导全表 | shell工具→命令注入 → 验证:实际触发工具副作用(OOB回连/读到文件)才写Fact
系统提示泄露/RAG投毒/过度授权跨租户越权/MCP插件供应链/资源成本攻击(烧token) | 输出处理:LLM输出进eval/SQL/前端→二次注入/存储XSS
模型文件: torch.load默认pickle→RCE | 发现端点:抓流量找/chat /agent /tool,问Agent"你有哪些工具"
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. 13d ago First seen · 19 lines · 62 tokens per session scan A 7286e92053f9

Subscribe to this mod's changes

ai-llm-app-attack is a skill published in the GitHub repository Ed1s0nZ/CyberStrikeAI (6,410 stars, last pushed 17d ago), licensed Apache-2.0. It adds 62 tokens to every session and 342 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

building-ioc-defanging-and-sharing-pipeline

Build an automated pipeline to defang indicators of compromise (URLs, IPs, domains, emails) for safe sharing and distribute them in STIX format through TAXII feeds and threat intelligence platforms.

26zl/cybersec-toolkit · 49 tokens

building-ioc-enrichment-pipeline-with-opencti

OpenCTI is an open-source platform for managing cyber threat intelligence knowledge, built on STIX 2.1 as its native data model. This skill covers building an automated IOC enrichment pipeline using O.

26zl/cybersec-toolkit · 52 tokens

collecting-threat-intelligence-with-misp

MISP (Malware Information Sharing Platform) is an open-source threat intelligence platform for gathering, sharing, storing, and correlating Indicators of Compromise (IOCs) of targeted attacks, threat.

26zl/cybersec-toolkit · 48 tokens

ai-llm-security-review

Use for AI/LLM security assessments, prompt injection, RAG security, agent/tool permissioning, model supply chain, LLM red teaming, AI governance, eval design, data leakage, jailbreak testing, and secure AI application review.

26zl/cybersec-toolkit · 55 tokens

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens