Add 55 new skills across 3 new domains + 6 undercovered areas (762 -> 817)

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.

skills/securing-agentic-ai-tool-invocation/references/api-reference.md

@@ -0,0 +1,49 @@
+# API Reference — Agentic AI Tool Invocation Controls
+
+## NVIDIA NeMo Guardrails
+
+Install: `pip install nemoguardrails`
+
+| API | Description |
+|-----|-------------|
+| `RailsConfig.from_path("./guardrails_config")` | Load rails config (config.yml, prompts.yml, *.co flows) |
+| `RailsConfig.from_content(yaml_content=..., colang_content=...)` | Load config inline |
+| `LLMRails(config)` | Build a guarded LLM wrapper |
+| `rails.generate(messages=[...])` | Run input/output/tool rails around generation |
+| `rails.register_action(fn, name=...)` | Register a custom tool/action under rail control |
+
+Built-in flows: `self check input`, `self check output`, `self check facts`. Rail types: `input`, `output`, `dialog`, `retrieval`, `execution/tool`.
+
+## jsonschema
+
+Install: `pip install jsonschema`
+
+| API | Description |
+|-----|-------------|
+| `validate(instance=args, schema=schema)` | Raise `ValidationError` if args violate schema |
+| `additionalProperties: false` | Deny-by-default extra arguments |
+| `pattern` / `maxLength` / `enum` | Constrain argument values (e.g. recipient domain allowlist) |
+
+## AWS STS (boto3) — scoped identity
+
+Install: `pip install boto3`
+
+| API | Description |
+|-----|-------------|
+| `sts.assume_role(RoleArn, RoleSessionName, Policy, DurationSeconds)` | Assume a role with an inline session policy that *further restricts* permissions |
+| `DurationSeconds=900` | Short-lived (15 min) credentials, least privilege |
+| `boto3.Session(aws_access_key_id=..., aws_session_token=...)` | Use the scoped creds for the tool call |
+
+## Policy decision contract
+
+| Decision | Meaning | Action |
+|----------|---------|--------|
+| `allow` | Allowlisted, args valid, low impact | Execute tool |
+| `require_approval` | High-impact tool | Route to human-in-the-loop, fail-closed |
+| `deny` | Unknown tool or invalid args | Reject and log |
+
+## External References
+
+- NeMo Guardrails docs: https://docs.nvidia.com/nemo/guardrails/
+- jsonschema docs: https://python-jsonschema.readthedocs.io/
+- OWASP Agentic AI Top 10: https://genai.owasp.org/resource/agentic-ai-threats-and-mitigations/

skills/securing-agentic-ai-tool-invocation/references/standards.md

@@ -0,0 +1,32 @@
+# 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