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 ir-playbook-data-exfiltrationgit 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/ir-playbook-data-exfiltration)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-data-exfiltration"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-data-exfiltration/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/ir-playbook-data-exfiltration"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-data-exfiltration.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 | $0.00101 | $0.02114 |
| Opus 5.5 | $0.00040 | $0.00846 |
| Sonnet 5 | $0.00020 | $0.00423 |
| Haiku 4.5 | $0.00010 | $0.00211 |
Grade A, and why
ir-playbook-data-exfiltration scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. Host evidence: `get_agent_processes` (rclone, curl/wget loops, 7z/rar, cloud sync clients, PowerShell uploads); How it starts
The opening of the file, as written. The whole thing — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IR Playbook — Data Exfiltration
Severity high → critical depending on data classification and whether transfer is ongoing. Regulated data
(PII/PHI/cardholder) can start breach-notification clocks, so record timestamps precisely. Rule IDs are from the
stock Wazuh 4.14 ruleset (levels official). Full procedure, forensic commands and notification templates:
references/playbook.md.
1. Detection signals
Stock Wazuh coverage for exfiltration is thin: it detects staging and some transfer tooling on Windows, cloud-provider findings, and USB storage. Volume thresholds and DNS tunnelling need network telemetry plus custom rules.
| Technique | Stock Wazuh rules (level) | Needs |
|---|---|---|
| T1560.001 Archive staging (Windows) | rules 92212 (L14, compression by PowerShell), 92210 (L6, compression in Users\Public), 91846 (L10, PowerShell .NET compression), 91825 (L4), 91821 (L4, archive of a filesystem search) | Sysmon Event ID 11, PowerShell/Operational |
| T1567.002 Exfil to cloud storage | rule 92038 (L12, connection to a cloud resource started by a script/binary) | Sysmon Event ID 1 |
| T1114 Email collection | rule 91845 (L10, Outlook add-in loaded by PowerShell) | PowerShell/Operational |
| T1052.001 Removable media | rule 81101 (L3, USB storage attached) | Linux kernel USB logs |
| T1537 / cloud exposure | rules 99855 (L12, S3 public read), 99856 (L12, S3 public write), 65061 (L3, GCP bucket permissions modified) | AWS Security Hub / GCP integrations |
| EDR telemetry (if integrated) | rules 99548 (L12), 99567 (L13), 99586 (L15) — Microsoft Graph "system is performing data exfiltration" | MS Graph integration |
Org-custom rules (the stock ruleset has none; create in range 100000–120000 and validate with wazuh-logtest):
| Behaviour | Suggested custom rule |
|---|---|
| T1041 / T1030 outbound volume (> 500 MB/h per host, or > 10 Mbps sustained 30 min) | custom rule 100501 / custom rule 100502 on firewall/NetFlow/Zeek logs, <same_source_ip /> |
| T1048.003 DNS tunnelling (long/encoded labels, > 100 queries/min, Base64 in TXT) | custom rule 100520, custom rule 100521, custom rule 100522 on DNS server or Zeek dns.log |
| Large archive in temp/staging dirs (Linux) | custom rule 100530 — child of FIM rules 554, 550 on staging paths with a size threshold |
| Uploads to unsanctioned cloud storage / webmail | custom rule 100550, custom rule 100551 on proxy logs with an allowlist of sanctioned domains |
| DLP policy violation | custom rule 100560 on your DLP product's decoder |
| Uploads to non-approved S3 / Azure / GCP buckets | custom rule 100570, custom rule 100571, custom rule 100572 on cloud audit logs |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 111 lines · 101 tokens per session scan A e96224e40886
ir-playbook-data-exfiltration is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 2,114 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-25.
Other skills, from other repositories
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-benchmark-suite
Agent skill for benchmark-suite - invoke with $agent-benchmark-suite.
agent-performance-monitor
Agent skill for performance-monitor - invoke with $agent-performance-monitor.
agent-resource-allocator
Agent skill for resource-allocator - invoke with $agent-resource-allocator.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.