security-compliance-tools — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited security-compliance-tools (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Tools and methodologies that help organisations assess, evidence, and maintain EU compliance posture. Not a generic security tool catalogue — any frontier model already knows how to run Semgrep.
The foundation of every risk assessment. Before you can assess compliance, you need to know what matters.
The NCSC (Dutch National Cyber Security Centre) uses the term "te beschermen belangen" (TBB) — literally "interests to be protected" — for what is commonly called critical assets or crown jewels. The methodology below preserves the original Dutch terminology where it references NCSC source material.
Source: NCSC — Hoe breng ik mijn te beschermen belangen in kaart?
.compliance/profile.json has a critical_assets array. If empty, guide the user through identification.Use these to help the user identify their critical assets through conversation:
| Skill | What it does | When to use |
|---|---|---|
| data-sensitivity | Classify data, scan for PII/credentials, detect secrets in prompts, enforce blocking | Before processing user data, on every incoming prompt |
| audit-logging | Structured logging for agent actions + enforce logging in AI-generated code | Every session — log tool calls and decisions |
| nis2-gap-analysis | 5-level maturity assessment with consultant field methodology | NIS2/Cbw compliance posture assessment |
| eu-compliance-directives | Curated EU source index — look up, don't hardcode | Regulation status checks |
When available in the environment, use these. They produce evidence for compliance dossiers.
| Resource | What it provides |
|---|---|
| [EU_compliance_MCP](https://github.com/Ansvar-Systems/EU_compliance_MCP) | Full-text search across 49 EU regulations (2,500+ articles), cross-regulation comparison, ISO 27001/NIST CSF control mappings, evidence requirements per article, sector-based applicability rules |
Install: npx @ansvar/eu-regulations-mcp (local) or add as MCP server in Claude Desktop / Cursor / Copilot.
When available, prefer over web lookups for: exact article text (verbatim EUR-Lex), comparing requirements across NIS2/DORA/GDPR/AI Act/CRA, mapping ISO 27001 or NIST CSF controls to regulation articles, and looking up what auditors expect as evidence.
Key tools: search_regulations, get_article, compare_requirements, map_controls, check_applicability, get_evidence_requirements.
| Resource | What it provides | Link |
|---|---|---|
| NCSC Zelfevaluatie NIS2 | Dutch NIS2 self-assessment questions aligned with Cbw | ncsc.nl |
| CCB CyFun | Belgian Cybersecurity Framework — 5 maturity levels, maps to NIS2 | ccb.belgium.be |
| BSI IT-Grundschutz | German baseline protection — detailed control catalogue | bsi.bund.de |
| ENISA Risk Management Toolbox | EU-wide risk assessment methodology for NIS2 entities | enisa.europa.eu |
| Resource | What it provides |
|---|---|
| Register van verwerkingsactiviteiten | Art. 30 record of processing — template + guidance |
| DPIA framework | Data Protection Impact Assessment for high-risk processing (Art. 35) |
| Verwerkersovereenkomst template | Processor agreement template aligned with Art. 28 |
| Skill | Source | What it adds |
|---|---|---|
| baz-scm/secure-coding | LobeHub / GitHub | OWASP-aligned code review patterns for agentic workflows |
| baz-scm/keep-secrets-out | GitHub | Pre-commit secret detection, rotation procedures |
| DefenseClaw | GitHub | AI agent runtime security — admission control for skills/MCP servers, CodeGuard static analysis (secrets, injection, unsafe exec), LLM prompt/response guardrails, tool call inspection, audit logging with SIEM export. Not EU-specific but complements complisec's data-sensitivity and audit-logging enforcement at the infrastructure layer. |
This is the consulting methodology that turns generic compliance checklists into an organisation-specific risk picture.
1. Org profile intake → populate .compliance/profile.json
2. Critical asset identification → map crown jewels using NCSC methodology
3. Supplier & SaaS mapping → catalogue dependencies, mark suppliers touching critical assets
4. Legal obligation scan → determine which regulations apply (NIS2, GDPR, AI Act, DORA)
5. Gap analysis → run nis2-gap-analysis against critical assets
6. Risk identification → for each critical asset: what threats exist? Cross-reference supplier risks
7. Prioritisation → rank by (critical asset criticality x threat likelihood). Build roadmap.The agent should guide the user through this workflow in order. Don't skip steps — an org that hasn't identified its critical assets can't meaningfully do a gap analysis.
search_regulations to cite exact article text and compare_requirements when the user's profile lists multiple regulations in legal[].~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.