mirror of
https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git
synced 2026-06-26 19:54:37 +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.
33 lines
1.7 KiB
Markdown
33 lines
1.7 KiB
Markdown
# Standards and References — Securing Agentic AI Tool Invocation
|
|
|
|
## MITRE ATLAS References
|
|
|
|
| Technique ID | Name | Tactic | Rationale |
|
|
|--------------|------|--------|-----------|
|
|
| AML.T0053 | LLM Plugin Compromise | Execution | Agent tools/plugins are the asset these controls protect |
|
|
| AML.T0051 | LLM Prompt Injection | ML Attack Staging | Injection is the primary vector that abuses tool invocation |
|
|
| AML.T0051.001 | LLM Prompt Injection: Indirect | Initial Access | Indirect injection via tool results drives unauthorized calls |
|
|
| AML.T0057 | LLM Data Leakage | Exfiltration | Excessive agency leads to leakage that these controls prevent |
|
|
|
|
## NIST AI RMF References
|
|
|
|
| ID | Name | Rationale |
|
|
|----|------|-----------|
|
|
| GOVERN-1.3 | Processes, procedures, and practices are in place to determine and manage AI risks and benefits | Governance of autonomous tool invocation (allowlisting, approvals, audit) |
|
|
|
|
## OWASP Agentic AI Top 10
|
|
|
|
| Class | Name | Rationale |
|
|
|-------|------|-----------|
|
|
| Tool Misuse | Agent abuses available tools | Allowlist + argument validation mitigates |
|
|
| Excessive Agency | Agent acts beyond intended scope | Policy gate + HITL mitigates |
|
|
| Privilege Compromise | Agent escalates via broad credentials | Scoped identity binding mitigates |
|
|
|
|
## Official Resources
|
|
|
|
- NVIDIA NeMo Guardrails: https://github.com/NVIDIA/NeMo-Guardrails
|
|
- OWASP Agentic AI threats & mitigations: https://genai.owasp.org/resource/agentic-ai-threats-and-mitigations/
|
|
- MITRE ATLAS: https://atlas.mitre.org/
|
|
- AWS STS session policies: https://docs.aws.amazon.com/IAM/latest/UserGuide/access_policies.html#policies_session
|
|
- NIST AI RMF: https://www.nist.gov/itl/ai-risk-management-framework
|