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 gmh5225/awesome-ai-security --skill adversarial-mlgit clone --depth 1 https://github.com/gmh5225/awesome-ai-securityWrote 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/gmh5225/awesome-ai-security/adversarial-ml)<a href="https://agentmods.dev/skills/gmh5225/awesome-ai-security/adversarial-ml"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/adversarial-ml/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/gmh5225/awesome-ai-security/adversarial-ml"><img src="https://agentmods.dev/badge/skills/gmh5225/awesome-ai-security/adversarial-ml.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 | $0.00029 | $0.00525 |
| Opus 5 | $0.00015 | $0.00262 |
| Sonnet 5 | $0.00006 | $0.00105 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
adversarial-machine-learning 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.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Machine Learning
Scope
Use this skill when working on:
- Adversarial examples (perturbations that fool models)
- Data poisoning attacks
- Model backdoors and trojans
- Evasion attacks
- Membership inference and model inversion
Attack Taxonomy
Adversarial Examples
- White-box attacks (full model access)
- Black-box attacks (query-only access)
- Transferability attacks
- Physical-world adversarial examples
- Patch attacks
Poisoning Attacks
- Label flipping
- Clean-label poisoning
- Gradient-matching poisoning
- Backdoor insertion during training
Backdoor Attacks
- Trojan triggers (visual patterns, specific inputs)
- Instruction backdoors (for LLMs)
- Weight-space backdoors
- Supply chain backdoors
Evasion Attacks
- Feature-space evasion
- Problem-space evasion
- Adaptive attacks against defenses
Privacy Attacks
- Membership inference attacks (MIA)
- Model inversion attacks
- Training data extraction
- Model stealing/extraction
Defense Categories
- Adversarial training
- Certified robustness
- Input preprocessing
- Anomaly detection
- Differential privacy
Key Frameworks & Tools
- Adversarial Robustness Toolbox (ART) - IBM
- CleverHans - TensorFlow
- Foolbox - PyTorch/JAX/TensorFlow
- TextAttack - NLP adversarial attacks
- SecML - Secure ML library
Where to Add Links in README
- Adversarial example tools:
AI Security & Attacks → Adversarial Attacks - Poisoning/backdoor research:
AI Security & Attacks → Poisoning & Backdoors - Privacy attacks:
AI Security & Attacks → Privacy & Extraction - Defense libraries:
AI Security Tools & Frameworks → AI Security Libraries - Benchmarks:
Benchmarks & Standards
Notes
Keep additions:
- ML/AI security focused
- Non-duplicated URLs
- Prefer peer-reviewed or well-maintained tools
Data Source
For detailed and up-to-date resources, fetch the complete list from:
https://raw.githubusercontent.com/gmh5225/awesome-ai-security/refs/heads/main/README.md
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 · 91 lines · 29 tokens per session scan A 8c7ba0422f68
adversarial-machine-learning is a skill published in the GitHub repository gmh5225/awesome-ai-security (45 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 525 once invoked, about $0.0001 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.