owasp-llm-top10 SKILL.md skillA
owasp-llm-top10 from sigistry/marketplace is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add sigistry/marketplace/owasp-llm-top10@git:20260826.571bc2fPins git:20260826.571bc2f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- sigistry/marketplace
- Path
plugins/llm-app-hardener/skills/owasp-llm-top10/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260826.571bc2f, committed Aug 26, 2026
- First version recorded
- Jul 15, 2026
- Size
- 4,544 bytes
- Repository stars
- 3
- License
- MIT
This skill should be used when the user mentions "prompt injection", "jailbreak", "owasp llm", "llm security", "guardrails", "data exfiltration", "insecure output", "tool abuse", "indirect injection", or "is this agent safe". It provides the OWASP Top 10 for LLM Applications mapped to code-level signals, plus a library of concrete attack strings to test against.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# OWASP LLM Top 10 ## Purpose Provide a standardized, code-level lens for auditing LLM applications against the OWASP Top 10 for LLM Applications, so a security review of prompt construction and tool wiring is consistent and grounded in the source, not hand-waved. The recurring, highest-impact failure is **LLM01 prompt injection**: untrusted content (user text, retrieved documents, tool outputs, fetched web/email) is concatenated into a prompt and then read as instructions, driving the model, and any tool it can call, to do the attacker's bidding. This skill maps each risk to the code pattern that causes it, the mitigation, and a concrete attack to test with. ## The core mental model An LLM has no reliable boundary between "instructions" and "data." Everything in the context window is a candidate instruction. Security follows from three questions asked at every call site: 1. **Provenance**: is this text trusted (developer-authored) or untrusted (from a user, a document, a tool result, the web)? 2. **Capability**: what tools can the model call, and what can each tool do (read secrets? send data? mutate state?)? …
Read the whole file at its exact version.
How to install
mdr add sigistry/marketplace/owasp-llm-top10@sha256:5a9f9a42d212878aThe line at the top of this page pins the label git:20260826.571bc2f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_xm54oe7btyu7qww4)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 15, 2026 and Aug 26, 2026, about one every 42 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260826.571bc2f latest | 2026-08-26 | 571bc2f | 4,544 B | A | view · diff |
| git:20260715.6169119 | 2026-07-15 | 6169119 | 4,545 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (4544 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
sigistry/marketplace · 3 stars · license MIT · pushed 2026-11-06 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_xm54oe7btyu7qww4 GET https://markdownregistry.com/api/v1/resolve?ref=sigistry/marketplace/owasp-llm-top10 GET https://markdownregistry.com/api/v1/blob/5a9f9a42d212878a680c7b7defff722d66d7ca69f6621db64e9dfbb49ebb8fb6
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.