agentsclimarketplace

Ml security

Skill ShieldNet-360/secure-vibe/dist/agent-skills/.agents/skills/ml-security

SecureVibe — prevention-first security for AI-written code. Signed SKILL.md knowledge that makes AI coding assistants write secure code at generation time, plus a deterministic CI gate. Offline · keyless · Ed25519-signed. By ShieldNet360.

Install
npx -y skills add ShieldNet-360/secure-vibe --skill ml-security

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Model artifact loading (pickle vs safetensors), model & data poisoning, PII in training data, secrets in notebooks, model provenance / lineage — Applies to: when generating code that loads ML models from disk / Hub / S3; when generating data pipelines that ingest user content for training / fine-tuning; when generating ML notebooks or training / evaluation scripts

SKILL.md

2.5 KB, 474 tokens by cl100k_base, as published. Nobody here has run it

<!-- Native skill bundle for agent-skills (cross-tool convention). Generated by `secure-vibe dev regenerate`. --> <!-- Do not edit by hand; the source of truth is skills/ml-security/SKILL.md. -->

ML Model Security

Model artifact loading (pickle vs safetensors), model & data poisoning, PII in training data, secrets in notebooks, model provenance / lineage

ALWAYS

  • When loading models, use safetensors for PyTorch and Hugging Face; use weights_only=True with torch.load on PyTorch 2.4+; never load arbitrary .pkl / .pt files from untrusted sources.
  • Verify provenance / lineage of any third-party or externally fine-tuned model — known author, signed or hashed checkpoint, recorded source — before loading it.
  • Pin and hash model + dataset versions and record them, so a poisoned artifact can be traced and rolled back.
  • Scrub PII, credentials, and secrets from training / fine-tuning data — at the source (ingestion), at storage (encryption + access control), and in anything committed to the repo.
  • Treat ML notebooks as code: no plaintext credentials in cells or cell output, and clear outputs before committing.

NEVER

  • pickle.loads / joblib.load / dill.loads / torch.load an artifact fetched at runtime from an untrusted source. These deserializers execute arbitrary code by design.
  • Use a model fine-tuned or distributed by an external party without provenance / lineage verification.
  • Store training-data examples that contain PII in long-term storage without explicit consent, retention windows, and deletion APIs.
  • Hard-code OpenAI / Anthropic / Cohere API keys in notebooks or repo files. Use environment variables and the secret-detection skill.
  • Commit synthetic or generated training data without labeling it and reviewing it for inadvertent PII or leaked secrets.

KNOWN FALSE POSITIVES

  • Pre-publication academic models from trusted authors are often distributed as .pt checkpoints; convert to safetensors as a first step rather than rejecting them outright.
  • Synthetic data generation pipelines may legitimately produce raw model output that is then committed — make sure it is labeled and reviewed.

What ships with it: 1 file

1.0 KB alongside SKILL.md

Keep looking

Skills are one crate of 326,970. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.