Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gensecaihq/Wazuh-Autopilot --skill compliance-mappinggit clone --depth 1 https://github.com/gensecaihq/Wazuh-AutopilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/compliance-mapping)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/compliance-mapping"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/compliance-mapping/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/compliance-mapping"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/compliance-mapping.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.01445 |
| Opus 5.5 | $0.00028 | $0.00578 |
| Sonnet 5 | $0.00014 | $0.00289 |
| Haiku 4.5 | $0.00007 | $0.00145 |
Grade A, and why
compliance-mapping scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compliance Mapping
Translate security evidence into control language auditors accept. You report status and gaps; you don't certify compliance.
Tools
| Need | Tool |
|---|---|
| Framework check | run_compliance_check(framework="PCI-DSS", agent_id=...); framework is one of PCI-DSS, HIPAA, SOX, GDPR, NIST, ISO27001; omit agent_id for the whole environment |
| CIS benchmark / SCA results per agent | get_sca_policy_checks(agent_id) |
| ISO 27001 posture | get_iso27001_dashboard |
| ISO 27001 gaps | get_iso27001_gap_analysis |
| One ISO control | get_iso27001_control_detail(control_id="A.8.16") |
| Alerts tagged to ISO controls | get_iso27001_alerts |
Wazuh compliance tags
Stock Wazuh rules declare compliance mappings as groups in the ruleset (pci_dss_10.2.4,
gdpr_IV_32.2, hipaa_164.312.b, nist_800_53_AC.7, tsc_CC6.1, gpg13_7.1). In alerts
Wazuh emits them as arrays: rule.pci_dss, rule.gdpr, rule.hipaa, rule.nist_800_53,
rule.tsc, rule.gpg13. For example, rule 5712 (sshd brute force) carries PCI DSS
10.2.4 / 10.2.5 / 11.4, NIST 800-53 AC.7 / AU.14 / SI.4, HIPAA 164.312.b and TSC
CC6.1 / CC6.8 / CC7.2 / CC7.3.
- Use them as evidence hints:
get_wazuh_alertson the scope and period, then count alerts per tag to show that monitoring for a requirement is producing events. - They map detections to requirements. They don't prove a control is effective.
Pair them with SCA results (
get_sca_policy_checks) for configuration requirements. - There is no ISO 27001 tag in the stock ruleset. The MCP ISO tools
(
get_iso27001_*) do that mapping server-side. - The PCI tags refer to the requirement numbering the rule was written against. Check it against v4.0.1 wording before citing it in an audit statement.
Load wazuh-sca-hardening for CIS benchmark and SCA detail (rule 19011 is a check that
went from passed to failed, level 9).
Framework anchors (category level — cite specific controls only when confident)
| Topic | ISO 27001:2022 Annex A | PCI DSS v4.0.1 | NIST 800-53r5 | CIS v8.1 |
|---|---|---|---|---|
| Logging & monitoring | A.8.15 Logging, A.8.16 Monitoring activities | Req 10 | AU family, SI-4 | Control 8 |
| Incident management | A.5.24–A.5.28 | Req 12.10 | IR family | Control 17 |
| Vulnerability mgmt | A.8.8 Management of technical vulnerabilities | Req 6, Req 11 | RA-5, SI-2 | Control 7 |
| Access control / accounts | A.5.15–A.5.18, A.8.2, A.8.5 | Req 7, Req 8 | AC, IA families | Controls 5, 6 |
| Configuration / hardening | A.8.9 Configuration management | Req 2 | CM family | Control 4 |
| Malware protection | A.8.7 | Req 5 | SI-3 | Control 10 |
| File integrity | A.8.9 / A.8.16 (supporting) | Req 11.5 (change detection) | SI-7 | Control 3 (data protection, supporting) |
| Network security | A.8.20–A.8.22 | Req 1 | SC family | Controls 12, 13 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 91 lines · 69 tokens per session scan A 978ecdee5017
compliance-mapping is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,445 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
external-privacy-guard
A privacy rule set for conversations that include people other than the account owner. It checks who is participating and limits what personal or confidential information may be shared.
agent-crdt-synchronizer
Agent skill for crdt-synchronizer - invoke with $agent-crdt-synchronizer.
agent-topology-optimizer
Agent skill for topology-optimizer - invoke with $agent-topology-optimizer.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-repo-architect
Agent skill for repo-architect - invoke with $agent-repo-architect.