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-suspicious-powershellgit 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-suspicious-powershell)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/ir-playbook-suspicious-powershell"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-suspicious-powershell/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-suspicious-powershell"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/ir-playbook-suspicious-powershell.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 | $0.00093 | $0.02159 |
| Opus 5.5 | $0.00037 | $0.00864 |
| Sonnet 5 | $0.00019 | $0.00432 |
| Haiku 4.5 | $0.00009 | $0.00216 |
Grade A, and why
ir-playbook-suspicious-powershell 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IR Playbook — Suspicious PowerShell
Severity medium → critical depending on payload and follow-on activity. MITRE ATT&CK: T1059.001, T1027,
T1140, T1105, T1566.001, T1003, T1547.001, T1112, T1562.001. Rule IDs are from the stock Wazuh 4.14 ruleset
(levels official). Coverage depends on Sysmon (group sysmon_eid1_detections etc.) and
PowerShell/Operational script-block logging (Event ID 4104; group powershell) being collected.
Full procedure and decoding guidance: references/playbook.md.
1. Detection signals
| Behaviour | Wazuh rules (level) | Source |
|---|---|---|
| Base64 / encoded command | rules 92057 (L12, PowerShell spawned PowerShell with base64 command), 91809 (L10, Base64 decoding in script), 92071 (L12, WMI-spawned PowerShell with base64) | Sysmon Event ID 1, script block |
| Office / mshta launch chain (phishing) | rules 92047 (L12, Office started mshta), 92048 (L15, and ran script), 92050 (L12, Office → verclsid), 92156 (L12, Office loaded vbeui.dll), 92214 (L15, Office-created suspicious file) | Sysmon Event IDs 1 / 7 / 11 |
| Script from suspicious location / launched by suspicious parent | rules 92029 (L6), 92065 (L6), 92062 (L14, unusual integrity level) | Sysmon Event ID 1 |
| In-memory / API abuse | rules 91810 (L10, CreateThread API), 91837 (L4, Invoke-Expression / Get-Content -Stream), 92151 (L12, PowerShell automation DLL loaded by a non-PowerShell process) | script block, Sysmon Event ID 7 |
| Download / payload drop | rules 92203 (L6, executable created by PowerShell), 92204 (L9, executable in AppData temp), 92205 (L9, executable in Windows root), 92073 (L6, PowerShell running certutil decode), 92018 (L13, certutil decoding a binary) | Sysmon Event IDs 1 / 11 |
| Defender tampering | rules 92008 (L12, real-time monitoring disabled), 92009, 92010, 92011, 92012, 92013, 92014, 92015 (all L13, individual Defender protections disabled) | Sysmon Event ID 1 |
| Credential access | rules 92024 (L14, SAM hive copied from VSS), 92026 (L14, reg.exe SAM dump), 92900 (L12, LSASS read access) | Sysmon Event IDs 1 / 10 |
| Persistence | rules 91844 (L12, startup registry entry via PowerShell), 92226 (L14, executable copied to startup folder), 92301 (L12, suspicious extension in a Run key), 89502 (L14, WMI consumer running a command) | script block, Sysmon Event IDs 11 / 13 / 20 |
| Remote execution | rule 91823 (L14, Invoke-Command on a remote computer) | script block |
| Discovery / collection (context only) | rules 91815, 91816, 91817, 91819 (all L4), 91824 (L4, clipboard), 91846 (L10, .NET compression) | script block |
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 · 98 lines · 93 tokens per session scan A f9f1c6d25613
ir-playbook-suspicious-powershell is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 93 tokens to every session and 2,159 once invoked, about $0.0004 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
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.