mirror of
https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
synced 2026-07-25 13:50:59 +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.
1.7 KiB
1.7 KiB
Standards and References — Prompt Injection Testing in RAG Pipelines
MITRE ATLAS References
| Technique ID | Name | Tactic | Rationale |
|---|---|---|---|
| AML.T0051 | LLM Prompt Injection | ML Attack Staging / Initial Access | Injected instructions in retrieved context override system intent |
| AML.T0051.001 | LLM Prompt Injection: Indirect | Initial Access | Payload delivered through ingested documents, not direct user input |
| AML.T0057 | LLM Data Leakage | Exfiltration | RAG injections aim to leak system/other-tenant documents |
| AML.T0024 | Exfiltration via ML Inference API | Exfiltration | Model responses act as the document exfiltration channel |
NIST AI RMF References
| ID | Name | Rationale |
|---|---|---|
| MEASURE-2.7 | AI system security and resilience are evaluated and documented | Injection probing measures the security/resilience of the RAG system |
OWASP Top 10 for LLM Applications (2025)
| ID | Name | Rationale |
|---|---|---|
| LLM01:2025 | Prompt Injection | Primary risk tested, including indirect injection via retrieval |
| LLM02:2025 | Sensitive Information Disclosure | Successful injections often exfiltrate private corpus data |
| LLM08:2025 | Vector and Embedding Weaknesses | Embedding-space retrieval poisoning surface |
Official Resources
- MITRE ATLAS: https://atlas.mitre.org/
- OWASP LLM01:2025 Prompt Injection: https://genai.owasp.org/llmrisk/llm01-prompt-injection/
- NVIDIA garak: https://github.com/NVIDIA/garak
- Promptfoo RAG red teaming: https://www.promptfoo.dev/docs/red-team/rag/
- Microsoft PyRIT: https://github.com/Azure/PyRIT
- NIST AI RMF: https://www.nist.gov/itl/ai-risk-management-framework