ai-ml-security — Skills — getagentictools

What it does

llm-prompt-injection for LLM-specific prompt injection, jailbreaking, and tool abuse techniques

deserialization-insecure for deeper coverage of Python pickle and general deserialization attack patterns

dependency-confusion when the ML pipeline has supply chain risks via pip/npm package confusion

Files with .pt/.pkl extension instead of .safetensors

Custom Python code in the repository (.py files outside standard config)

Unusual config.json with trustremotecode=True requirement

Model card lacking provenance, training data description, or eval results

ai ml security

Source

Repository: https://github.com/yaklang/hack-skills

ai-ml-security FAQ

What does the ai-ml-security skill do?

>- AI/ML security playbook. Use when assessing model supply chain attacks (pickle RCE, poisoned weights), adversarial examples, model poisoning, model stealing, data privacy attacks (membership inference, model inversion), and autonomous agent security risks. llm-prompt-injection for LLM-specific prompt injection, jailbreaking, and tool abuse techniques deserialization-insecure for deeper coverage of Python pickle and general deserialization attack patterns

What does ai-ml-security require?

Principle: Tools with side effects should require explicit user confirmation. Read-only tools can be auto-approved with logging.

How do I install ai-ml-security?

Run: npx -y skills add https://github.com/yaklang/hack-skills --skill ai-ml-security --agent claude-code — the source lives at github.com/yaklang/hack-skills.

Maintain ai-ml-security?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[ai-ml-security on getagentictools](https://getagentictools.com/skills/yaklang-hack-skills-ai-ml-security?ref=badge)

npx agentictools info skills/yaklang-hack-skills-ai-ml-security

The second line is the CLI lookup for this page — handy in READMEs and docs.