llm-app-security

llm-app-security is a skill for Claude Code, Codex from BagelHole/DevOps-Security-Agent-Skills. It costs 24 tokens per session (8,130 once invoked), scanned B, original, MIT.

A security guide for applications powered by large language models (LLMs), including chatbots, document question-answering tools, and AI features in SaaS products. It covers input checks, output controls, tenant separation, and abuse prevention.

In plain words
What is it for?
Use it when building customer-facing or internal AI features, RAG applications, developer assistants, or multi-tenant services that send user text to an LLM.
Why use it?
It helps protect user and company data while reducing prompt attacks, unsafe responses, misuse, and accidental access between customers.

Skill for Claude CodeCodex

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

Good fit Use it when building customer-facing or internal AI features, RAG applications, developer assistants, or multi-tenant services that send user text to an LLM.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bagelhole/devops-security-agent-skills/llm-app-security
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 BagelHole/DevOps-Security-Agent-Skills --skill llm-app-security
Clone the repo
git clone --depth 1 https://github.com/BagelHole/DevOps-Security-Agent-Skills

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 llm-app-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/llm-app-security/github.svg)](https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/llm-app-security)
Your own site
<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/llm-app-security"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/llm-app-security/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 llm-app-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/bagelhole/devops-security-agent-skills/llm-app-security"><img src="https://agentmods.dev/badge/skills/bagelhole/devops-security-agent-skills/llm-app-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,130 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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: 4 findings, 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 Prompt Injection · line 89
    This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.
    Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
  • high Memory Poisoning · line 910
    Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.
    Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
  • medium System Prompt Leakage · line 104
    Skill contains patterns that could indirectly extract system prompts through rephrasing, translation, summarization, or side-channel techniques.
    Fix: Guard against indirect extraction by refusing to summarize, translate, or rephrase system instructions. Add explicit anti-extraction clauses.
  • medium Data Exfiltration · line 151
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00024 $0.08130
Opus 5 $0.00012 $0.04065
Sonnet 5 $0.00005 $0.01626
Haiku 4.5 $0.00002 $0.00813

Measured 6d ago against content hash 5b48ec511061, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

llm-app-security scanned grade B 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 6d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

# Patterns that signal an attempt to override system instructions

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

security/ai/llm-app-security/SKILL.md · 1,018 lines

How it starts

The opening of the file, as written. The whole thing — 1,018 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LLM Application Security

Harden chatbots, RAG pipelines, and AI features embedded in SaaS products against prompt injection, data leakage, abuse, and compliance violations.


When to Use

Apply this skill whenever you are building or operating:

  • Customer-facing chatbots -- support bots, sales assistants, or any conversational UI backed by an LLM.
  • RAG-augmented applications -- internal knowledge bases, document Q&A, or code assistants that retrieve context from a vector store before generating a response.
  • AI features inside SaaS products -- summarization, auto-complete, content generation, or classification endpoints exposed to end users.
  • Internal copilots -- developer tools, HR bots, or finance assistants that handle sensitive corporate data.
  • Multi-tenant platforms -- any system where multiple customers share the same LLM infrastructure.

If your application sends user-controlled text to an LLM and returns the result, every section below applies.


OWASP LLM Top 10 -- Risk Map and Mitigations

The OWASP Top 10 for LLM Applications (2025) defines the most critical risks. The table below maps each risk to concrete controls implemented later in this document.

# Risk Key Mitigation Section
LLM01 Prompt Injection Input validation, instruction hierarchy Input Validation, System Prompt Protection
LLM02 Insecure Output Handling Output sanitization, PII scrubbing Output Safety
LLM03 Training Data Poisoning Document ingestion scanning Secure RAG Pipeline
LLM04 Model Denial of Service Per-user token budgets, rate limiting Rate Limiting
LLM05 Supply Chain Vulnerabilities Pin model versions, verify checksums Compliance
LLM06 Sensitive Information Disclosure PII detection, tenant isolation Output Safety, Tenant Isolation
LLM07 Insecure Plugin Design Tool allowlists, parameter validation System Prompt Protection
LLM08 Excessive Agency Least-privilege tool scopes System Prompt Protection
LLM09 Overreliance Provenance tracking, confidence scores Secure RAG Pipeline
LLM10 Model Theft Access controls, API key rotation Rate Limiting, Compliance

Read the full file on GitHub · 1,018 lines

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. 6d ago First seen · 1,018 lines · 24 tokens per session scan B 5b48ec511061

Subscribe to this mod's changes

llm-app-security is a skill published in the GitHub repository BagelHole/DevOps-Security-Agent-Skills (1,071 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 8,130 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Related

Other skills, from other repositories

bedrock

AWS Bedrock foundation models for generative AI. Use when invoking foundation models, building AI applications, creating embeddings, configuring model access, or implementing RAG patterns.

itsmostafa/aws-agent-skills · 36 tokens

aws-bedrock-ai

WORKFLOW SKILL — Amazon Bedrock and AWS AI design: foundation model selection, knowledge bases (RAG), agents for bedrock, guardrails, provisioned throughput, batch inference, fine-tuning, KMS, VPC endpoints, regional GA, and per-provider licensing.

odere-pro/claude-aws-architect · 65 tokens

jetson-inference-mem-tune

Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.

NVIDIA/skills · 50 tokens

neuron-test-engineer

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…

neuron-core/neuron-ai · 94 tokens

neuron-rag-specialist

Implement RAG (Retrieval-Augmented Generation) with Neuron AI including vector stores, embeddings providers, document loaders, and retrieval strategies. Use this skill whenever the user mentions RAG, retrieval, vector search, document retrieval, semantic search, knowledge bases, chat with documents, or wants to build…

neuron-core/neuron-ai · 95 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens