LLM risk assess — audit LLM apps against the OWASP Top 10 for LLM Applications 2025 (short listing)
⚠️ Dual-use — authorized use only. Short listing — license not verifiable; comprehensive LLM security assessment: threat modeling, injection probes, all 10 OWASP LLM 2025 risks, red team testing
- What
- ⚠️ Dual-use — authorized use only. Short listing — license not verifiable; comprehensive LLM security assessment: threat modeling, injection probes, all 10 OWASP LLM 2025 risks, red team testing
- Cost
- Free
- Needs
- an LLM-integrated application, RAG pipeline, or AI agent that you own or are explicitly authorized to security-test
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Selected by Skill Harbor — ⚠️ Dual-use — AUTHORIZED USE ONLY: this is a defensive security playbook, but it ships real attack techniques (prompt injection probes, jailbreak testing, defense-bypass and evasion testing, system-prompt extraction) — use it only on systems you own or are explicitly authorized to test. Short listing (the discovery manifest records NOASSERTION — the manifest makes faith, so no content is reproduced beyond this summary): @owasp's llm-risk-assess play: a structured security assessment of LLM-integrated applications against the OWASP Top 10 for LLM Applications 2025 — architecture and threat modeling (data flows, trust boundaries, RAG and tool integration mapping), automated security testing, coverage of all ten risk categories (prompt injection, sensitive information disclosure, supply chain, data and model poisoning, improper output handling, excessive agency, system prompt leakage, vector/embedding weaknesses, misinformation, unbounded consumption) with real-world attack scenarios, red team testing, and a remediation roadmap with code examples. Honest caveats: license terms not verifiable — short listing with a link only; the allowed-tools list includes Bash and WebFetch, so the agent can run real probes — keep it sandboxed and scoped to authorized targets. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
LLM risk assess is a free Muse skill and short listing for comprehensive LLM security assessment. It covers threat modeling, injection probes, all ten OWASP LLM 2025 risks, and red team testing. Dual-use, authorized use only: it ships real attack techniques, so use it only on systems you own or are explicitly authorized to test.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 1b5fd4cStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an LLM-integrated application, RAG pipeline, or AI agent that you own or are explicitly authorized to security-test Install "LLM risk assess — audit LLM apps against the OWASP Top 10 for LLM Applications 2025 (short listing)" for me. It gives my agent @owasp's llm-risk-assess play: map the architecture and threat model (LLM provider, data flows, RAG components, trust boundaries), run automated security testing (injection probes, secret scans, vector DB checks), assess all 10 OWASP LLM 2025 risks with attack scenarios, run red team tests, and produce a risk matrix with findings, proof-of-concept examples, and a remediation roadmap. IMPORTANT: dual-use — authorized use only; run probes only against systems I own or am authorized to test. License terms were not verifiable (the discovery manifest records NOASSERTION) — fetch from the link only, reproduce nothing beyond the link, and read the license terms yourself before reuse. Repository: https://raw.githubusercontent.com/owasp/secure-agent-playbook/1b5fd4cff76075feb56d61ee2985e82516f8c53b/plugins/ai-security-skills/skills/llm-risk-assess/SKILL.md Pinned version: install the code at commit 1b5fd4cff76075feb56d61ee2985e82516f8c53b exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "llm-risk-assess". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. confirm which application I am authorized to assess, read the license terms before reuse). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 1b5fd4c · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026 · Observed during the install test: files.pythonhosted.org, pypi.org
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.