Identify DLP coverage gaps across AI-era exfiltration channels.
npx skills add https://github.com/blamejs/exceptd-skills --skill dlp-gap-analysis
Please help me install this Agent Skill. Skill: dlp-gap-analysis Source: https://github.com/blamejs/exceptd-skills/tree/main/skills/dlp-gap-analysis Command: npx skills add https://github.com/blamejs/exceptd-skills --skill dlp-gap-analysis
Legacy data loss prevention (DLP) tools are built for network-centric, on-prem environments and completely miss AI-era exfiltration channels including LLM prompts, MCP tool-call arguments, RAG retrievals, embedding-store queries, and code-completion telemetry. This Skill eliminates the risk of false compliance confidence by identifying these gaps and mapping them to real-world threat patterns and cross-jurisdictional privacy requirements.
Use the dlp-gap-analysis skill to run a full audit of your organization's DLP coverage for AI-era exfiltration channels and generate a prioritized gap report mapped to your applicable compliance frameworks.
High-intent search queries and answers about installing and using this skill.
To audit DLP controls for AI exfiltration channels, enumerate LLM prompt egress, MCP tool arguments, RAG retrievals, and embedding-store queries to identify coverage gaps that legacy network-centric tools fail to monitor. This maps blind spots to global compliance regimes and MITRE ATLAS TTPs.
Data loss prevention gaps under GDPR or HIPAA include failing to inspect LLM prompt content containing PHI under TLS and lacking MCP gateway inspection. These AI-channel blind spots are mapped against NIST 800-53, ISO 27001, and 35 other frameworks to ensure compliance.
Map AI security gaps to MITRE ATLAS TTPs by applying the RWEP scoring model aligned with ATT&CK v19.1. This prioritizes remediation based on real-world exploitation risk, AI-acceleration potential, and regulatory exposure across modern exfiltration channels.
Legacy DLP does not work effectively for AI-powered development environments because it misses code-completion telemetry leaks and IDE telemetry. A targeted gap analysis is required to identify these uninspected channels and implement SDK-level prompt logging as compensating controls.
You can use a gap analysis to generate compliance audit reports for RAG systems by assessing embedding-store membership inference and corpus retrieval coverage. It flags insufficient controls and produces a prioritized report mapped to applicable global privacy regulations.
The RWEP scoring model prioritizes AI data exfiltration risk by evaluating real-world exploitation potential, AI-acceleration factors, and regulatory exposure. It aligns with MITRE ATLAS v2026.06 and ATT&CK v19.1 TTPs to guide compensating control implementation.
anthropicsTrack compliance requirements and audit readiness across SOC 2, ISO 27001, and GDPR frameworks.
8GG-GitIdentify, categorize, and prioritize technical debt with remediation plans.
RedHatProductSecurityCreate isolated container or microVM environments to validate AI-generated code and commands.
roanbrasilTrace LLM calls and track token costs across LangSmith, LangFuse, and Phoenix.
