creator/Anthropic-Cybersecurity-Skills
1
0
Fork 0
mirror of https://github.com/mukul975/Anthropic-Cybersecurity-Skills.git synced 2026-09-04 07:20:50 +03:00
Code Issues Packages Projects Releases Wiki Activity

feat: enrich 209 skills with MITRE ATLAS, D3FEND, and NIST AI RMF frontmatter

Browse Source 
Added structured security framework mappings to SKILL.md frontmatter across all applicable skills:
- atlas_techniques: MITRE ATLAS v5.5 AML.TXXXX IDs (81 skills, AI-targeted attack techniques)
- d3fend_techniques: MITRE D3FEND v1.3 defensive technique labels (139 skills, mapped from ATT&CK IDs)
- nist_ai_rmf: NIST AI RMF 1.0 subcategory IDs (85 skills, AI risk management functions)

Also updates ATTACK_COVERAGE.md with coverage statistics for all three frameworks.
This commit is contained in:
mukul975
2026-04-06 01:56:17 +02:00
parent c15f73db46
commit ef27f026cb
209 changed files with 3959 additions and 3379 deletions
Download Patch File Download Diff File Expand all files Collapse all files
skills/implementing-llm-guardrails-for-security/SKILL.md
+32 -10
View File
@@ -1,21 +1,43 @@
---
name: implementing-llm-guardrails-for-security
description: >
Implements input and output validation guardrails for LLM-powered applications to prevent
prompt injection, data leakage, toxic content generation, and hallucinated outputs. Builds
a security validation pipeline using NVIDIA NeMo Guardrails Colang definitions, custom Python
validators for PII detection and content policy enforcement, and the Guardrails AI framework
for structured output validation. The guardrails system intercepts both user inputs (blocking
injection attempts, stripping PII, enforcing topic boundaries) and model outputs (detecting
hallucinations, filtering toxic content, validating JSON schema compliance). Activates for
requests involving LLM output validation, AI content filtering, guardrail implementation,
description: 'Implements input and output validation guardrails for LLM-powered applications to prevent prompt injection,
data leakage, toxic content generation, and hallucinated outputs. Builds a security validation pipeline using NVIDIA NeMo
Guardrails Colang definitions, custom Python validators for PII detection and content policy enforcement, and the Guardrails
AI framework for structured output validation. The guardrails system intercepts both user inputs (blocking injection attempts,
stripping PII, enforcing topic boundaries) and model outputs (detecting hallucinations, filtering toxic content, validating
JSON schema compliance). Activates for requests involving LLM output validation, AI content filtering, guardrail implementation,
or LLM safety enforcement.
'
domain: cybersecurity
subdomain: ai-security
tags: [LLM-guardrails, NeMo-Guardrails, input-validation, output-filtering, AI-safety]
tags:
- LLM-guardrails
- NeMo-Guardrails
- input-validation
- output-filtering
- AI-safety
version: 1.0.0
author: mukul975
license: Apache-2.0
atlas_techniques:
- AML.T0051
- AML.T0054
- AML.T0056
- AML.T0057
- AML.T0062
nist_ai_rmf:
- GOVERN-1.1
- GOVERN-6.1
- MEASURE-2.7
- MEASURE-2.5
- MANAGE-2.4
d3fend_techniques:
- Content Validation
- Content Filtering
- Content Excision
- Application Hardening
- Execution Isolation
---
# Implementing LLM Guardrails for Security