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 transilienceai/communitytools --skill ai-threat-testinggit clone --depth 1 https://github.com/transilienceai/communitytoolsWrote 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/transilienceai/communitytools/ai-threat-testing)<a href="https://agentmods.dev/skills/transilienceai/communitytools/ai-threat-testing"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/ai-threat-testing/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/transilienceai/communitytools/ai-threat-testing"><img src="https://agentmods.dev/badge/skills/transilienceai/communitytools/ai-threat-testing.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 | $0.01140 |
| Opus 5 | $0.00028 | $0.00570 |
| Sonnet 5 | $0.00011 | $0.00228 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
ai-threat-testing 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Threat Testing
Test LLM applications for OWASP LLM Top 10 vulnerabilities using 10 specialized agents. Use for authorized AI security assessments.
Quick Start
1. Specify target (LLM app URL, API endpoint, or local model)
2. Select scope: Full OWASP Top 10 | Specific vulnerability | Supply chain
3. Agents deploy, test, capture evidence
4. Professional report with PoCs generated
Coverage — OWASP LLM Top 10, 2025 edition
Which file addresses which category is decided by
reference/catalog/llm-top10-2025.json, not by the
filename. The llmNN- prefixes on disk predate the 2025 renumbering and no longer match; the
content is correct, the labels were not. Cite an id only with its edition (LLM06:2025), because a
bare LLM06 means two different categories depending on which edition the reader assumes.
| Category | Attack surface |
|---|---|
LLM01:2025 Prompt Injection |
Direct and indirect injection, instruction override, filter evasion |
LLM02:2025 Sensitive Information Disclosure |
Training-data and cross-tenant RAG leakage, canary verification |
LLM03:2025 Supply Chain |
Dependency CVEs, model provenance, malicious serialized models |
LLM04:2025 Data and Model Poisoning |
Backdoor triggers, membership inference, behavioural anomalies |
LLM05:2025 Improper Output Handling |
Code/XSS injection downstream, unsafe deserialization |
LLM06:2025 Excessive Agency |
Tool/plugin abuse, privilege escalation, unauthorised actions — the category that matters for agents rather than chatbots |
LLM07:2025 System Prompt Leakage |
Gap — no playbook yet. See the catalogue: what the prompt contains is a separate finding from whether it can be extracted |
LLM08:2025 Vector and Embedding Weaknesses |
RAG injection, retrieval manipulation, embedding inversion |
LLM09:2025 Misinformation |
Hallucination and confidence manipulation where output is relied upon |
LLM10:2025 Unbounded Consumption |
Token flooding, cost impact, and model extraction/theft (2025 treats extraction-by-query as a consumption problem) |
What ships with it
25 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/adversarial-pixel-attacks.md 5.3 KB
- reference/agentic-tool-hijacking.md 7.2 KB
- reference/catalog/llm-top10-2025.json 6.5 KB
- reference/gradient-leakage-attacks.md 5.4 KB
- reference/hopfield-recovery.md 4.6 KB
- reference/llm01-prompt-injection.md 3.4 KB
- reference/llm02-insecure-output.md 2.9 KB
- reference/llm03-training-poisoning.md 3.4 KB
- reference/llm04-resource-exhaustion.md 3.0 KB
- reference/llm05-supply-chain.md 4.0 KB
- reference/llm06-excessive-agency.md 4.0 KB
- reference/llm07-model-extraction.md 4.1 KB
- reference/llm08-vector-poisoning.md 3.9 KB
- reference/llm09-overreliance.md 4.1 KB
- reference/llm10-logging-bypass.md 4.6 KB
- reference/malicious-keras-model-triage.md 5.0 KB
- reference/scenarios/llm/llm01-prompt-injection-direct.md 3.6 KB
- reference/scenarios/llm/llm01-prompt-injection-indirect.md 3.8 KB
- reference/scenarios/llm/llm02-insecure-output-handling.md 3.7 KB
- reference/scenarios/llm/llm03-training-data-poisoning.md 3.8 KB
- reference/scenarios/llm/llm04-denial-of-service.md 3.9 KB
- reference/scenarios/llm/llm05-supply-chain-vulnerabilities.md 5.8 KB
- reference/scenarios/llm/llm06-sensitive-info-disclosure.md 3.6 KB
- reference/scenarios/llm/llm07-insecure-plugin-design.md 3.8 KB
- reference/scenarios/llm/llm08-excessive-agency.md 3.6 KB
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.
- 10d ago First seen · 108 lines · 55 tokens per session scan A 1cb1b256b1c5
ai-threat-testing is a skill published in the GitHub repository transilienceai/communitytools (520 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,140 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
Web Application Security Testing
OWASP Top 10 testing, injection vulnerability detection, API security assessment, authentication testing, and web vulnerability reporting for authorized assessments.
identity-auth
Test identity, authentication, authorization, and sessions.
business-logic
Test workflows, state transitions, pricing, and concurrency.
command-execution
Security-focused command execution techniques for penetration testing. Use this skill when executing system commands during authorized security assessments. Covers Windows and Linux command execution, common security testing commands, and best practices for avoiding detection.
pentest-validation
Orchestrate security finding validation through graduated exploitation. 4-phase pipeline: recon (SAST/DAST), analysis (code review), validation (exploit proof), report (No Exploit, No Report gate). Eliminates false positives by proving exploitability.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.