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.
npx skills add 26zl/cybersec-toolkit --skill ai-llm-security-reviewgit clone --depth 1 https://github.com/26zl/cybersec-toolkitWrote 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.
[](https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-llm-security-review)<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-llm-security-review"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/ai-llm-security-review/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.
<a href="https://agentmods.dev/skills/26zl/cybersec-toolkit/ai-llm-security-review"><img src="https://agentmods.dev/badge/skills/26zl/cybersec-toolkit/ai-llm-security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00371 |
| Opus 5 | $0.00028 | $0.00186 |
| Sonnet 5 | $0.00011 | $0.00074 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
ai-llm-security-review 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 11d 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.
What it actually says
AI and LLM security review
Use this skill for AI applications, agents, RAG systems, model gateways, prompt chains, evals, and LLM governance.
Review workflow
- Inventory the AI system: model/provider, prompts, tools, RAG sources, memory, logs, user roles, secrets, data classes, and downstream actions.
- Threat model trust boundaries:
- user input to prompt
- retrieved content to model
- model output to tools
- tool output to user
- logs/traces to operators
- Test high-risk paths:
- direct and indirect prompt injection
- data exfiltration from RAG or memory
- insecure tool invocation
- overbroad agent permissions
- jailbreaks that change policy or role
- model/provider key leakage
- training/eval data contamination
- Recommend controls:
- least-privilege tool scopes
- allowlisted tool schemas and argument validation
- retrieval filtering and source attribution
- secret redaction before prompts/logs
- output validation before side effects
- human approval for destructive or external actions
- continuous evals and regression prompts
Deliverables
Return findings as:
| Risk | Attack path | Impact | Evidence | Control | Test to keep fixed |
|---|
When the task involves current AI regulation or sector obligations, verify against current official sources before making definitive claims.
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.
- 11d ago First seen · 44 lines · 55 tokens per session scan A e58b380bdfc4
ai-llm-security-review is a skill published in the GitHub repository 26zl/cybersec-toolkit (54 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 371 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
vector-and-embedding-weaknesses
Hunt vector / embedding weaknesses (OWASP LLM08:2025) — adversarial inputs against the RAG / similarity layer that cause cross-tenant leak, embedding-inversion privacy loss, semantic confusion, and retriever-driven prompt injection.
sensitive-information-disclosure
Hunt LLM sensitive-information disclosure (OWASP LLM02:2025) — leakage of PII, secrets, internal source, model details, and other-tenant data through model outputs, training-data extraction, or retrieval-side joins.
aatmf-t12-rag-poisoning
AATMF T12 — RAG & Knowledge Base Manipulation. PoisonedRAG, vector store flood, embedding collision, retrieval-bias attacks.
recon-ai-enrichment
Wiring an LLM into a recon tool's decisions ("let AI pick {feature} for {tool}"): the never-raise contract, the per-target cache, the full+partial coverage, and the two UI toggles bound to one field. A raising AI helper or an empty fallback silently breaks or disables a live scan. Trigger: adding or editing a recon AI…
llm-provider-integration
Adding an LLM provider to RedAmon: the credential boundary (keys must never reach scan containers), prefix-routed model ids, and the provider registry. A misrouted model id or a leaked key are the two failures this guards. Trigger: adding or editing an LLM provider; editing parsemodelprovider in…
implementing-cloud-dlp-for-data-protection
Implementing Cloud Data Loss Prevention (DLP) using Amazon Macie, Azure Information Protection, and Google Cloud DLP API to discover, classify, and protect sensitive data across cloud storage, databases, and data pipelines.