mirror of
https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
synced 2026-07-26 14:10:59 +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.
1.4 KiB
1.4 KiB
Standards and Framework Mapping — Red-Teaming LLMs with garak
MITRE ATLAS (Adversarial Threat Landscape for AI Systems)
| ID | Name | Rationale |
|---|---|---|
| AML.T0051 | LLM Prompt Injection | garak's promptinject and latentinjection probes craft inputs that override intended model instructions; the scanner measures how often the target obeys the injected directive. |
| AML.T0054 | LLM Jailbreak | garak's dan and related probes attempt to push the model past its safety guardrails so it produces restricted output; the detector verdict measures jailbreak success. |
Reference: https://atlas.mitre.org/
NIST AI Risk Management Framework (AI RMF 1.0)
| ID | Function/Subcategory | Rationale |
|---|---|---|
| MEASURE-2.7 | AI system security and resilience are evaluated and documented | garak produces repeatable, quantitative measurements (per-probe hit rates) of an LLM's resistance to injection, jailbreak, and leakage, directly evidencing this subcategory. |
Reference: https://www.nist.gov/itl/ai-risk-management-framework
OWASP Top 10 for LLM Applications (cross-reference)
| OWASP ID | Risk | garak probe family |
|---|---|---|
| LLM01:2025 | Prompt Injection | promptinject, latentinjection, encoding, dan |
| LLM02:2025 | Sensitive Information Disclosure | leakreplay, xss |
| LLM07:2025 | System Prompt Leakage | leakreplay |
Reference: https://genai.owasp.org/