Moai Ref LLM Security
modu-ai/moai-adk
AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and…
Application security defense knowledge for builders. An agent skill from telagod/code-abyss.
Install Defending Applications
$ npx skills add telagod/code-abyss --skill defending-applications -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install telagod/code-abyss defending-applications --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/defending-applications .claude/skills/defending-applications && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .claude/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/telagod/code-abyss/tree/main/skills/defending-applicationsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add telagod/code-abyss --skill defending-applications -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install telagod/code-abyss defending-applications --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/defending-applications .agents/skills/defending-applications && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .agents/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add telagod/code-abyss --skill defending-applications -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install telagod/code-abyss defending-applications --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/defending-applications .cursor/skills/defending-applications && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .cursor/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/telagod/code-abyss.git --path skills/defending-applications--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add telagod/code-abyss --skill defending-applications -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install telagod/code-abyss defending-applications --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/defending-applications .gemini/skills/defending-applications && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .gemini/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install telagod/code-abyss defending-applicationsInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add telagod/code-abyss --skill defending-applications -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/defending-applications .github/skills/defending-applications && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .github/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add telagod/code-abyss --skill defending-applications -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install telagod/code-abyss defending-applications --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/telagod/code-abyss.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/defending-applications .opencode/skills/defending-applications && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "defending-applications" agent skill from https://github.com/telagod/code-abyss/tree/main/skills/defending-applications into .opencode/skills/defending-applications/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "defending-applications", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
defending-applications- GitHub stars
- 243
- Token cost
- ~777 tokens
- SKILL.md length
- 183 words
- Files
- 4 (incl. references)
- Skills in repo
- 38
- Repo updated
- First seen
- Licence
- MIT
At a glance
Application security defense knowledge for builders. An agent skill from telagod/code-abyss.
- Works in 3 steps: 入口在哪：用户可控数据从哪进来（route/header/cookie/body/… → 信任边界在哪：何处由"untrusted"变"trusted"，是否有显式校验。 → 检测信号是什么：修复后若被绕过，哪条日志/指标会响。
- Reviewing application-layer defenses
- SKILL.md covers 路由, 何时使用, 联动 and 执行链, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Defending Applications is an agent skill from telagod/code-abyss. Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning, agent privilege escalation, output filtering). Use when designing or reviewing application-layer defenses, fixing CVE-class bugs in your own code, hardening auth flows, or threat-modeling LLM-powered…
Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/llm-appsec.md`, `references/oauth-and-sessions.md` and `references/web-api-appsec.md`).
It sits in Security, covering Authentication, Web application vulnerabilities and OAuth and OpenID Connect. It works with GraphQL. The repository describes itself as: Give your AI coding agent a personality. Composable persona + style + skills for Claude Code, Codex, Gemini CLI & OpenClaw. Ships Tech Persona Card v1.0 spec. The licence is MIT.
When your agent uses it
- Reviewing application-layer defenses
- Fixing CVE-class bugs in your own code
- Hardening auth flows
- Threat-modeling LLM-powered features
Example prompts
- “/defending-applications”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 入口在哪：用户可控数据从哪进来（route/header/cookie/body/file/upstream API/RAG doc）。
- 信任边界在哪：何处由"untrusted"变"trusted"，是否有显式校验。
- 检测信号是什么：修复后若被绕过，哪条日志/指标会响。
What it can do on your machine
Read from SKILL.md and the folder at commit 2544577. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Defending Applications loads about 777 tokens when it runs, and up to ~6.8k if it reads all its reference files. Until then it costs about 178 tokens; SKILL.md has 183 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from telagod/code-abyss at commit 2544577, republished under its MIT licence (© telagod). 183 words, ~777 tokens.
Download SKILL.mdSave it as
.claude/skills/defending-applications/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- defending-applications
- description
- Application security defense knowledge for builders. Covers Web/API/GraphQL hardening (XSS/SQLi/SSRF/IDOR/BOLA/Mass Assignment/deserialization/upload/path traversal), authentication/authorization (OAuth 2.0/OIDC/JWT/Session/Cookie/SAML/SSO), and LLM application security (prompt injection, jailbreak, RAG poisoning, agent privilege escalation, output filtering). Use when designing or reviewing application-layer defenses, fixing CVE-class bugs in your own code, hardening auth flows, or threat-modeling LLM-powered features. For offensive testing see securing-systems/pentest, for incident response see securing-systems/blue-team, for infra-layer hardening see provisioning-infrastructure.
- user-invocable
- false
应用安全防御 · 镇魔甲
判断先于执行：决定「是否做 / 选什么 / 如何取舍」（栈、方案、架构、权衡）前，先读领域判断内核
skills/_kernel/security/SKILL.md——它管 judgment，本秘典管 execution；冲突时以内核判断为准。
开发侧防御秘典：站在 builder 一侧，把漏洞挡在合并前。 不教渗透，只教"如何写出杀不动的代码"和"如何把已生漏洞最小代价闭环"。 信级：项目源码/lock 文件 > 框架官方安全文档 > CVE/CWE > 训练记忆（标
[unverified]）。
路由
| 意图 | 加载 | 触发词 |
|---|---|---|
| Web/API/GraphQL 漏洞防御 | web-api-appsec | XSS, SQLi, SSRF, BOLA, IDOR, Mass Assignment, GraphQL, 反序列化, 文件上传, 路径遍历, XXE, OWASP |
| 认证授权与会话 | oauth-and-sessions | OAuth, OIDC, JWT, SSO, SAML, Session, Cookie, PKCE, refresh token, kid 注入 |
| LLM 应用安全 | llm-appsec | Prompt 注入, 越狱, 越权调用, RAG 投毒, agent tool 滥用, 输出过滤, jailbreak |
何时使用
| 场景 | 使用本 skill | 使用其他 |
|---|---|---|
| review 自家代码、修 CVE、设计鉴权 | ✅ 本 skill | — |
| 写 SAST 规则、Semgrep 模式 | ✅ 本 skill + securing-systems/code-audit | — |
| 设计 LLM 应用的 guardrail | ✅ llm-appsec | + building-agent-systems/llm-security |
| 红队渗透、写 PoC 攻击目标 | ❌ | securing-systems/pentest |
| 处理已发生的入侵、日志取证 | ❌ | securing-systems/blue-team |
| 容器/K8s/CI 加固 | ❌ | provisioning-infrastructure |
| 设计零信任、身份架构 | 部分（OAuth/SSO 内） | architecting-security |
联动
- securing-systems/code-audit：本 skill 给"怎么修"，code-audit 给"怎么找"。
- securing-systems/pentest：攻方视角验证本 skill 的修复是否真正闭环。
- analyzing-security：自动化扫描胶水；本 skill 提供规则语义。
- building-agent-systems/llm-security：agent 内部细节；本 skill 关注应用边界。
- designing-architectures：威胁建模、API 设计；本 skill 关注落地代码。
执行链
威胁建模 → 入口梳理 → source→sink 追踪 → 防御层选型 → 最小修复 → 回归测试 → 检测信号埋点每个漏洞的修复必须回答三问：
- 入口在哪：用户可控数据从哪进来（route/header/cookie/body/file/upstream API/RAG doc）。
- 信任边界在哪：何处由"untrusted"变"trusted"，是否有显式校验。
- 检测信号是什么：修复后若被绕过，哪条日志/指标会响。
铁律
- 服务端为真：前端校验只是 UX，所有 authz/sanitize 必须在服务端再做一次。客户端代码即攻击面。
- deny by default：authz、CORS、CSP、SQL where 子句、文件类型——所有名单皆 allowlist 优先，blacklist 是反模式。
- 不信任 ID：URL/body 里的 object_id 永远先做 ownership 校验，再做业务逻辑。BOLA 是 API 漏洞之王。
- 可观测优先于完美防御：每个高风险路径必须有结构化日志 + 速率/异常告警，被绕过时能 5 分钟内发现。
- 修复要带回归：每个漏洞修复必须配 1 个攻击用例测试 + 1 个正常用例测试，否则六个月后必复发。
输出约束
- 漏洞示例代码统一
❌ 错代码/✅ 正代码对比，错代码必须能跑通漏洞场景。 - 攻击演示用
example.com/ RFC 5737 网段（192.0.2.0/24）；token/密钥用<REDACTED>。 - 给修复方案时同时给：检测信号（log key / metric name）、回归测试骨架、性能/兼容回归点。
© telagod, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 3 other files (references) in skills/defending-applications of telagod/code-abyss.
- SKILL.md
- references/llm-appsec.md
- references/oauth-and-sessions.md
- references/web-api-appsec.md
Open the folder on GitHubat commit 2544577
Compare with similar skills
Defending Applications next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Defending Applications this skilltelagod/code-abyss | 243 | — | ~777 | Automated safety check: Pass | MIT | |
| Moai Ref LLM Securitymodu-ai/moai-adk | 1.2k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Cybersecurityohmyjahh/xquads-squads | 276 | — | ~895 | Automated safety check: Pass | MIT | |
| Web2 Vuln ClassesGabson0x/bountyforge | 443 | — | ~11k | Automated safety check: Warn | None | |
| Moai Ref Secopsmodu-ai/moai-adk | 1.2k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Code Audit3stoneBrother/code-audit | 893 | 1 repos | ~2.7k | Automated safety check: Pass | None |
Similar skills
Cybersecurity
ohmyjahh/xquads-squads
Squad de 15 agentes de seguranca ofensiva e defensiva (Georgia Weidman, Peter Kim, Jim Manico, Chris Sanders, Omar Santos, Marcus Carey) cobrindo pentest, red team, blue team, AppSec, recon e…
Web2 Vuln Classes
Gabson0x/bountyforge
Complete reference for 28 web2 bug classes with root causes, detection patterns, bypass tables, exploit techniques, and real paid examples.
Moai Ref Secops
modu-ai/moai-adk
DevSecOps, container, and API operational defensive security reference: CI/CD pipeline hardening, secret scanning, IaC misconfiguration detection, SAST/DAST integration, container image scanning…
Code Audit
3stoneBrother/code-audit
Professional code security audit skill covering 55+ vulnerability types.
Auth Bypass
NeoTheCapt/RedteamAgent
Test for authentication and authorization flaws including credential attacks, session issues, and access control bypasses
More from telagod/code-abyss
All 38 skills in this repoSecurity Gate Scanner
telagod/code-abyss
Scans code with a bundled Node scanner for injection, secret leaks and other dangerous patterns, and requires documented decisions for accepted risks.
Persona Voice Card Builder
telagod/code-abyss
Distills a recurring agent voice from conversations into a restricted Persona Voice Card, validates it for schema, safety and distinctness, and prepares it for community submission.
Skill Cultivation Funnel
telagod/code-abyss
Distills repeated workflows into new skills, improves existing ones and promotes them through local, project and community tiers after a default-deny safety scan.
DOCX Processing Toolkit
telagod/code-abyss
Routes Word document tasks to the right tool: pandoc for text, raw OOXML for structure and comments, docx-js for new files, and a mandatory redlining flow for edits to others' documents.
PDF Processing Toolkit
telagod/code-abyss
Picks the right Python library or CLI tool for a PDF task, text and table extraction, merging, splitting, OCR, watermarking or form filling, and points to a matching recipe.
Code Change Analysis Gate
telagod/code-abyss
Checks what a code change touched, how far its impact reaches and whether design docs, tests and README files kept up, before commit or in review.
Related
Works with
Categories
Questions about Defending Applications
What does Defending Applications do?
Application security defense knowledge for builders. An agent skill from telagod/code-abyss. Defending Applications is an agent skill from telagod/code-abyss. Application security defense knowledge for builders.
When should I use Defending Applications?
Defending Applications fits situations like: reviewing application-layer defenses; fixing CVE-class bugs in your own code; hardening auth flows; threat-modeling LLM-powered features.
How do I install Defending Applications in Claude Code?
Run `npx skills add telagod/code-abyss --skill defending-applications -a claude-code`. Or copy the skill folder (skills/defending-applications in telagod/code-abyss) into .claude/skills/defending-applications in your project. Claude Code loads it when a task matches its description.
How do I install Defending Applications in Codex?
Run `npx skills add telagod/code-abyss --skill defending-applications -a codex`. Or copy the skill folder (skills/defending-applications in telagod/code-abyss) into .agents/skills/defending-applications in your project. Codex loads it when a task matches its description.
Can I use Defending Applications in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add telagod/code-abyss --skill defending-applications -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/defending-applications, .gemini/skills/defending-applications, .github/skills/defending-applications and .opencode/skills/defending-applications in your project.
What does Defending Applications need to run?
SKILL.md names no scripts, command-line tools or credentials: Defending Applications is instructions for the agent only.
Does Defending Applications access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Defending Applications safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Defending Applications use?
Defending Applications is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Defending Applications use?
About 777 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.1k tokens, read only when the agent opens those files.
What are the alternatives to Defending Applications?
Skills that share tags, products or a category with Defending Applications: Moai Ref LLM Security (modu-ai/moai-adk, 1.2k stars), Cybersecurity (ohmyjahh/xquads-squads, 276 stars), Web2 Vuln Classes (Gabson0x/bountyforge, 443 stars) and Moai Ref Secops (modu-ai/moai-adk, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Defending Applications?
telagod (a GitHub user) maintains it in telagod/code-abyss, which has 243 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on July 19, 2026.
Source: telagod/code-abyss on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.