CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

moai-ref-llm-security

AI/LLM defensive security reference: prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and guardrails, MITRE ATLAS defensive correlation, and NIST AI RMF governance. Agent-extending skill that amplifies backend, security, and AI-application engineering with production-grade defensive patterns for LLM-backed systems. NOT for: offensive techniques (jailbreak authoring, attack-payload crafting, red-team exploitation), model training or fine-tuning methodology, prompt optimization for capability, web-app OWASP Top 10 (see moai-ref-owasp-checklist), or general API design (see moai-ref-api-patterns).

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/moai-ref-llm-security/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, information-dense defensive reference with genuinely non-obvious content (OWASP LLM 2025 IDs, ATLAS correlations, a trust-boundary model) and a strong verification checklist. Its weaknesses are repetition between the OWASP overview table and the per-topic sections, repeated scope disclaimers, and a fully monolithic body that contradicts its own declared progressive-disclosure levels by shipping no second-level reference files.

Suggestions

Split the detailed mapping tables (OWASP LLM Top 10, MITRE ATLAS, poisoning matrix) into one-level-deep reference files under references/ and keep only the trust-boundary model and verification checklist inline, making the body actually match the declared 3000-token level-2 budget.

Deduplicate: the OWASP table rows for LLM01/LLM04/LLM05/LLM06 restate the later dedicated sections — keep the table as a one-line index (risk + control, pointer to section) or drop the redundant rows.

State the defensive review workflow as an explicit numbered procedure (classify channels → map to OWASP → apply controls → severity findings → verify checklist) and remove the repeated "this is defense, not attack" disclaimer, keeping it once at the top.

DimensionReasoningScore

Conciseness

The dense tables and the genuinely non-obvious material (OWASP LLM 2025 IDs, ATLAS technique IDs, the trust-boundary table) earn their tokens, but there is noticeable redundancy: the OWASP Top 10 table rows for LLM01/LLM04/LLM05/LLM06 restate the dedicated sections that follow, and the "defense, not attack" disclaimer is repeated at least five times ("never how to exploit it", "not an attack procedure", "never an attack method", "not an attack recipe", "never to provide an attack recipe"). This fits the 3 anchor (mostly efficient, some unnecessary explanation that could be tightened) better than 4.

3 / 5

Actionability

For an instruction-only reference skill the guidance is concrete and specific: named controls per layer ("instruction-hierarchy enforcement", "context-aware encoding: HTML escape, shell-quote, SQL parameter"), operational rules ("cap the number of tool invocations per task", "Verify cryptographic signatures on model weights and datasets before use"), a P0–P3 severity rubric with example findings, and an eight-item verification checklist. It stops short of 5 because there is no executable example of any control (no screening pattern, schema, or config snippet) — the how-to-implement layer is left to the reader.

4 / 5

Workflow Clarity

The implicit review workflow is coherent and ordered: classify channels as trusted/untrusted → map to OWASP LLM Top 10 → apply per-domain hardening → check red flags → verify, and the Verification section supplies explicit checkpoints ("show which items were evaluated", "re-validate tool results before re-prompting") that function as a validation gate. Not a 5 because the sequence is implied by section order rather than stated as an explicit procedure, and there is no error-recovery loop for findings (the severity table says what to do but not how to re-verify a fix).

4 / 5

Progressive Disclosure

There are no bundle files at all — the entire ~250-line body (OWASP table, ATLAS table, poisoning matrix, rationalizations, checklists) is inlined in SKILL.md, despite frontmatter declaring "progressive_disclosure: enabled" with a 3000-token level-2 budget the body roughly exceeds. Section headers are clear, so it is not the unstructured 2 anchor, but content that plainly belongs in per-domain reference files (e.g., the OWASP and ATLAS mapping tables) is inline, matching the 3 anchor.

3 / 5

Total

14

/

20

Passed

Description

70%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-bounded description with excellent negative-scope disambiguation against sibling skills, written in third person. Its main gaps are the missing inline "Use when..." trigger clause (parked in a separate when_to_use field) and one sentence of buzzword padding.

Suggestions

Append the trigger guidance from `when_to_use` ("Use when hardening an LLM-backed application or agent against prompt injection, designing guardrails...") to the description field itself so the description answers 'when' as well as 'what' — this would lift completeness from 3 to 5.

Delete or rewrite the sentence "Agent-extending skill that amplifies backend, security, and AI-application engineering with production-grade defensive patterns" — it is marketing fluff that adds no trigger terms or capabilities.

Add one or two plain-language trigger synonyms (e.g., "LLM app security", "jailbreak/prompt-injection defense") so users who don't know the OWASP LLM / ATLAS vocabulary can still find the skill.

DimensionReasoningScore

Specificity

The description lists seven concrete capability areas ("prompt-injection defense, OWASP LLM Top 10 defensive mapping, MCP and agentic tool-call hardening, training-data poisoning detection, model-output validation and guardrails, MITRE ATLAS defensive correlation, and NIST AI RMF governance"), which is comprehensive coverage of the domain. It falls short of a 5 because these are topic nouns rather than concrete actions, and the sentence "Agent-extending skill that amplifies backend, security, and AI-application engineering with production-grade defensive patterns" is marketing fluff the guidelines penalize.

4 / 5

Completeness

The "what" is clear and explicit, but the description itself contains no "Use when..." clause or equivalent trigger guidance — the trigger guidance lives in a separate `when_to_use` frontmatter field, which the description rubric does not credit. Per the guideline that a missing 'Use when...' clause caps completeness at 3, this scores 3; it is above 2 because the what is fully specific and the NOT-for list partially implies scope.

3 / 5

Trigger Term Quality

Strong natural-term coverage for this domain: "prompt-injection", "guardrails", "MCP", "agentic", "tool-call", "OWASP LLM", "MITRE ATLAS", "NIST AI RMF", "hardening", "output validation", "AI/LLM defensive security" — the exact vocabulary a security engineer would use. Not a 5 because plainer user phrasings (e.g., "secure my LLM app", "chatbot safety", "jailbreak defense") are absent, and jailbreak appears only in the NOT-for exclusion list.

4 / 5

Distinctiveness Conflict Risk

A clear niche (LLM-specific defensive security) with an explicit exclusion list disambiguating the nearest neighbors: "NOT for: offensive techniques..., model training or fine-tuning methodology, prompt optimization..., web-app OWASP Top 10 (see moai-ref-owasp-checklist), or general API design (see moai-ref-api-patterns)". This is the strongest possible conflict-risk posture — explicit redirects to sibling skills for every overlapping domain — matching the 5 anchor.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

modu-ai/moai-adk

Path

.claude/skills/moai-ref-llm-security/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.