mirror of
https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
synced 2026-07-18 05:29:40 +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.
1.9 KiB
1.9 KiB
Standards and Framework Mapping
NIST AI Risk Management Framework (AI RMF 1.0 / GenAI Profile NIST AI 600-1)
| ID | Name | Rationale |
|---|---|---|
| MEASURE-2.7 | AI system security and resilience are evaluated and documented | Assessing inversion, membership, isolation, and poisoning weaknesses measures the security/resilience of the RAG vector layer. |
MITRE ATLAS
| ID | Name | Rationale |
|---|---|---|
| AML.T0024 | Exfiltration via ML Inference API | Parent technique: query/embedding access is abused to exfiltrate source data. |
| AML.T0024.000 | Infer Training Data Membership | Membership-inference probe determines whether a record is in the corpus. |
| AML.T0024.001 | Invert ML Model | Embedding inversion reconstructs source text from vectors. |
| AML.T0020 | Poison Training Data | Knowledge-base poisoning inserts adversarial chunks into the corpus. |
| AML.T0051.001 | LLM Prompt Injection: Indirect | Injection payloads surviving in retrieved chunks. |
OWASP Top 10 for LLM Applications (2025)
| ID | Name | Rationale |
|---|---|---|
| LLM08 | Vector and Embedding Weaknesses | The core risk class under test (inversion, leakage, poisoning). |
| LLM02 | Sensitive Information Disclosure | Inversion/membership leakage discloses sensitive source data. |
| LLM01 | Prompt Injection | Indirect injection delivered through poisoned retrieval. |
Weakness class to control mapping
| Weakness | Control |
|---|---|
| Embedding inversion | Authenticate + rate-limit embedding endpoint; avoid exposing raw scores. |
| Membership inference | Restrict similarity-score exposure; add query auditing. |
| Cross-tenant leakage | Server-side tenant filters or per-tenant collections/namespaces. |
| Knowledge-base poisoning | Provenance tagging, content validation, per-source retrieval caps. |
| Indirect injection in chunks | Sanitize retrieved text; apply output guardrails. |