What is security-owasp-llm?

A security review guide for features that use large language models, document retrieval, embeddings, fine-tuning, or several model providers. It traces data from user input through the model to any later action and checks relevant OWASP risks, where OWASP is a project that publishes common web and AI security risks.

Use it to review chatbots, retrieval-augmented generation systems, model-powered workflows, embedding systems, fine-tuned models, and agents that can call tools or affect other systems.

It helps find prompt injection, sensitive-data exposure, unsafe model output, excessive tool access, and uncontrolled cost or usage before release. Findings are checked with abuse cases and tests rather than trusting the model to behave correctly.

security-owasp-llm — Skill for Codex by ashermahonin/agentic-skills

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 ashermahonin/agentic-skills --skill security-owasp-llm

Clone the repo

git clone --depth 1 https://github.com/ashermahonin/agentic-skills

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/security-owasp-llm/github.svg)](https://agentmods.dev/skills/ashermahonin/agentic-skills/security-owasp-llm)

Your own site

<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/security-owasp-llm"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/security-owasp-llm/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ashermahonin/agentic-skills/security-owasp-llm"><img src="https://agentmods.dev/badge/skills/ashermahonin/agentic-skills/security-owasp-llm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 690 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.00690
Opus 5.5	$0.00035	$0.00276
Sonnet 5.5	$0.00017	$0.00138
Haiku 4.5	$0.00009	$0.00069

Measured 2mo ago against content hash 982e67b16c4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-owasp-llm 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 2mo 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.

agentic/skills/security-owasp-llm/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security: OWASP LLM Top 10

Purpose

Map the LLM data flow and review each applicable OWASP LLM category with concrete abuse cases. The release verdict must rely on tests and controls, not expected model behaviour.

Scope and evidence

Read references/owasp-llm-top10.md.
Map the LLM data flow: user input → preprocessing → prompt assembly → retrieval/embedding → model call → output handling → downstream effect. Note where untrusted data crosses into prompt context.
Identify the model(s), provider(s), tool(s), and the agent's permitted actions.
Use Context7 MCP for the current OWASP LLM Top 10 wording and the current model-provider security guidance (Anthropic, OpenAI, Google, Mistral, Meta, etc.).

Assessment

For each LLM Top 10 category, mark status: Pass / Concern / Fail / Out-of-scope.
Build an abuse-case list per category: e.g., direct prompt injection, indirect via retrieved doc, system-prompt leakage probe, jailbreak via tool description, exfil via embedding inversion, denial via context blow-up.
Verify each abuse case with an eval: at least 10 representative prompts per category, multiple seeds, varied phrasing, plus at least one obfuscated/encoded variant.
Cross-check with security-owasp-agentic for autonomy/agency risk and with security-secrets for prompt content secrets handling.
Produce remediation plan, owner per finding, and a release-gate verdict with conditions.

Safety rules

Use Context7 MCP for current LLM Top 10 categories, provider safety docs, and any model-card limitations.
Keep a decision trace: model version, evaluator method, abuse-case coverage, what is not yet tested.
Refuse to mark a category Pass without an eval run, not just a code review.
Escalate any unmitigated Excessive Agency or Sensitive Information Disclosure finding before release.

Security record

LLM data-flow diagram (sources, sinks, trust boundaries)
Per-category status table with eval evidence
Abuse-case eval results (counts, rates, examples)
Findings register with owners
Release-gate verdict and conditions

Read the full file on GitHub · 56 lines

Files

What ships with it

2 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.

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.

2mo ago First seen · 56 lines · 87 tokens per session scan A 982e67b16c4e

Subscribe to this mod's changes

security-owasp-llm is a skill published in the GitHub repository ashermahonin/agentic-skills (10 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 690 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.

Data and AI RAG and vectors Security

security-owasp-llm next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
security-owasp-llmashermahonin/agentic-skills	Skill	10	2mo ago	MIT	A	87	Codex
embeddingsruvnet/ruflo	Skill	81k	yesterday	MIT	A	62	Claude Code
agent-platform-rag-engine-managementgoogle/skills	Skill	22k	yesterday	Apache-2.0	A	85	Claude Code, Codex
llm-app-patternsdavila7/claude-code-templates	Skill	33k	yesterday	MIT	A	54	Claude Code, Codex
9router-embeddingsdecolua/9router	Skill	32k	9d ago	MIT	A	66	Claude Code, Codex
embedding-strategiesforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	3d ago	Apache-2.0	A	37	Claude Code, Codex
similarity-search-patternsforyourhealth111-pixel/Vibe-Skills	Skill	3.8k	3d ago	Apache-2.0	A	30	Claude Code, Codex