mirror of
https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
synced 2026-07-16 12:45:17 +03:00
mukul975
8cae0648ec
Demand-driven expansion targeting the fastest-growing 2025-2026 threat and
skills categories (ISC2/WEF/CrowdStrike/Mandiant signals):
- AI Security (NEW domain, 12 skills): LLM red-teaming with garak/PyRIT,
prompt injection (direct/indirect/RAG), MCP tool-poisoning, agentic tool
invocation, guardrails, model/data poisoning, system-prompt leakage,
embedding/vector weaknesses, model extraction, continuous red-teaming
- Supply Chain Security (NEW domain, 5 skills): SBOMs, dependency confusion,
malicious-npm triage, typosquatting, SLSA/Sigstore provenance
- Hardware & Firmware Security (NEW domain, 4 skills): CHIPSEC/UEFI audit,
Secure Boot bypass, TPM measured-boot attestation, ESP bootkit hunting
- Identity (10): Entra ID/ROADtools, GraphRunner, AADInternals, ADCS/Certipy,
shadow credentials, coercion, BloodHound CE, device-code phishing, SSO abuse
- Cloud-native (8): Stratus, Pacu, CloudFox, container escape, K8s RBAC,
Falco, Trivy, kube-bench
- Offensive C2 (6): Sliver, Havoc, NetExec, DPAPI, NTLM relay ESC8, redirectors
- DFIR (6): Hayabusa, Chainsaw, KAPE, Velociraptor, EZ Tools, Plaso
- Backfill (4): OpenCTI, MISP, honeytokens, post-quantum crypto migration
Each skill follows the repo taxonomy (SKILL.md + references/{standards,api-reference}.md
+ scripts/agent.py + LICENSE), with researched real tool commands (no placeholders),
complete frontmatter, and ATT&CK/ATLAS + NIST CSF mappings. Updates README domain
table, skill count, and index.json.
49 lines
2.2 KiB
Markdown
49 lines
2.2 KiB
Markdown
# API Reference — Data and Model Poisoning Detection
|
|
|
|
## Adversarial Robustness Toolbox (ART)
|
|
|
|
Install: `pip install adversarial-robustness-toolbox`
|
|
|
|
| API | Description |
|
|
|-----|-------------|
|
|
| `from art.estimators.classification import KerasClassifier` | Wrap a Keras model for ART (also `PyTorchClassifier`, `TensorFlowV2Classifier`) |
|
|
| `from art.defences.detector.poison import ActivationDefence` | Activation-clustering poisoning detector (Chen et al., 2018) |
|
|
| `ActivationDefence(classifier, x_train, y_train)` | Construct the defense |
|
|
| `defence.detect_poison(nb_clusters=2, nb_dims=10, reduce="PCA")` | Returns `(report, is_clean_lst)`; `is_clean_lst[i]==0` => poisoned |
|
|
| `from art.defences.detector.poison import SpectralSignatureDefense` | Spectral-signature poisoning detector |
|
|
| `SpectralSignatureDefense(classifier, x, y, expected_pp_poison=0.05, batch_size=128, eps_multiplier=1.5)` | Construct |
|
|
| `defence.detect_poison()` | Returns `(report, is_clean_lst)` |
|
|
|
|
## Cleanlab
|
|
|
|
Install: `pip install cleanlab`
|
|
|
|
| API | Description |
|
|
|-----|-------------|
|
|
| `from cleanlab.filter import find_label_issues` | Find mislabeled samples |
|
|
| `find_label_issues(labels, pred_probs, return_indices_ranked_by="self_confidence")` | Ranked indices of label issues |
|
|
| `from cleanlab.outlier import OutOfDistribution` | Outlier / OOD detection |
|
|
| `from cleanlab import Datalab` | End-to-end data audit (label, outlier, near-duplicate) |
|
|
|
|
## safetensors (safe serialization)
|
|
|
|
Install: `pip install safetensors`
|
|
|
|
| API | Description |
|
|
|-----|-------------|
|
|
| `from safetensors.numpy import load_file` | Load weights without executing pickle |
|
|
| `from safetensors.torch import load_file` | PyTorch variant |
|
|
|
|
## Integrity commands
|
|
|
|
| Command | Purpose |
|
|
|---------|---------|
|
|
| `sha256sum model.safetensors` | Compute weight digest to compare to published value |
|
|
| `find ./models -name "*.pt" -o -name "*.bin" -o -name "*.pkl"` | Locate unsafe pickle-based artifacts |
|
|
|
|
## External References
|
|
|
|
- ART defenses docs: https://adversarial-robustness-toolbox.readthedocs.io/en/latest/modules/defences/detector_poisoning.html
|
|
- Cleanlab docs: https://docs.cleanlab.ai/
|
|
- safetensors: https://github.com/huggingface/safetensors
|