audit-llm-security SKILL.md skillB
This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.
audit-llm-security from kensaurus/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kensaurus/skills/audit-llm-security@git:20260923.68c095ePins git:20260923.68c095e in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kensaurus/skills
- Path
skills/audit-llm-security/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260923.68c095e, committed Sep 23, 2026
- First version recorded
- Aug 18, 2026
- Size
- 6,835 bytes
- Repository stars
- 9
- License
- MIT
Read-only OWASP LLM Top 10 audit of app-facing AI: prompt injection, data leakage, unsafe output or agency, RAG risks, unbounded spend. Use when "audit LLM security", "prompt injection", "jailbreak my chatbot", or "is my AI safe?".
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
# audit-llm-security — OWASP LLM Top 10 **Degree of freedom: MIXED** — Phases 0–1 `[HIGH freedom]`; Phase 2 live probes `[LOW freedom — run exactly]` (benign policy probes only; stop at evidence). Read-only. You verify that **user-facing** LLM features cannot be hijacked, leak secrets, or spend without a bound. **Quality/cost traces belong to `audit-langfuse-llm`; coding-agent policy belongs to `enhance-agent-guardrails`.** **The failure mode is silent:** a chatbot that looks helpful in demo will follow a pasted instruction, dump the system prompt, or call a privileged tool. > **Present findings. Do not patch until the user approves.** Never paste secret > values, full system prompts, or live API keys into the report. ## This skill vs neighbors | Skill | Owns | |---|---| | **audit-llm-security** (this) | App-facing LLM attack surface (OWASP LLM Top 10) | | `audit-langfuse-llm` | Trace quality, evals, hallucination, cost observability | | `plan-llm-cost-guardrails` | Token budgets, circuit breakers, quota abuse | | `plan-input-validation` | Non-LLM trust boundaries (forms, XSS, webhooks) | …
Read the whole file at its exact version.
How to install
mdr add kensaurus/skills/audit-llm-security@sha256:721437f25dac8bc5The line at the top of this page pins the label git:20260923.68c095e, 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_vt2s742b37zggwdp)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 18, 2026 and Sep 23, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260923.68c095e latest | 2026-09-23 | 68c095e | 6,835 B | B | view · diff |
| git:20260923.cf348bd | 2026-09-23 | cf348bd | 6,895 B | B | view · diff |
| git:20260820.950107c | 2026-08-20 | 950107c | 6,882 B | B | view · diff |
| git:20260819.170df67 | 2026-08-19 | 170df67 | 6,909 B | B | view · diff |
| git:20260818.274c4d7 | 2026-08-18 | 274c4d7 | 5,342 B | B | view |
Audit of the latest version
- fail: No prompt-injection phrasing (matched: ignore previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6835 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 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
kensaurus/skills · 9 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_vt2s742b37zggwdp GET https://markdownregistry.com/api/v1/resolve?ref=kensaurus/skills/audit-llm-security GET https://markdownregistry.com/api/v1/blob/721437f25dac8bc5a0857357b2afebc8eca5d8f1ed7883cef63846e9636aac74
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.
More from kensaurus/skills
Every file in kensaurus/skills