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 host-forensicsgit 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/host-forensics)<a href="https://agentmods.dev/skills/gensecaihq/wazuh-autopilot/host-forensics"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/host-forensics/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/host-forensics"><img src="https://agentmods.dev/badge/skills/gensecaihq/wazuh-autopilot/host-forensics.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 | $0.00045 | $0.01349 |
| Opus 5.5 | $0.00018 | $0.00540 |
| Sonnet 5 | $0.00009 | $0.00270 |
| Haiku 4.5 | $0.00005 | $0.00135 |
Grade E, and why
host-forensics scanned grade E with 3 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
`~/.ssh/authorized_keys`, `/etc/rc.local`, `/etc/ld.so.preload`, shell profiles Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
| Encoded / obfuscated command lines (`-enc`, `FromBase64String`, `curl | sh`) | T1059, T1027 | Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| Encoded / obfuscated command lines (`-enc`, `FromBase64String`, `curl | sh`) | T1059, T1027 | How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Host Forensics
Remote, read-only live response through the Wazuh agent's inventory (syscollector) and alert history. You cannot image disks or run commands; you work from what the agent reports. Be explicit about that limitation in findings.
Procedure
- Identify the agent:
get_wazuh_agents(match name/IP) →agent_id, OS, version, last keepalive. check_agent_health— a disconnected or stale agent means inventory may be old; record the inventory timestamp. Syscollector inventories run on an interval (1 hour by default), so a short-lived process may never appear, and a killed one may still be listed until the next scan. Comparescan.timewith the incident time.get_agent_processes(agent_id)— review with the heuristics below.get_agent_ports(agent_id)— listening and established sockets.get_agent_configuration(agent_id)— confirm FIM/rootcheck/log collection is enabled; attackers disable monitoring.get_wazuh_alerts(agent_id=..., timestamp_start="now-7d")— FIM (rules 550, 553, 554; registry rules 594, 598, 750, 752), rootcheck (rule 510; rule 513 Windows malware), SCA (rule 19011 check passed → failed) and audit events for persistence evidence. Loadwazuh-fim-investigationandwazuh-malware-detectionfor detail.get_wazuh_vulnerabilities(agent_id)andget_sca_policy_checks(agent_id)— the likely way in (unpatched service, weak configuration) matters for eradication.
Suspicious process heuristics
| Signal | Why |
|---|---|
Interpreter children of web/database servers (w3wp, httpd, nginx, java, sqlservr → cmd, powershell, sh, bash) |
web shell / exploitation (T1505.003, T1059) |
Binaries running from /tmp, /dev/shm, /var/tmp, %TEMP%, %APPDATA%, C:\Users\Public |
staging / malware |
Names mimicking system binaries in wrong paths (svchost.exe outside System32, [kworker] with a real exe path) |
masquerading (T1036) |
Encoded / obfuscated command lines (-enc, FromBase64String, `curl |
sh`) |
Known tools: mimikatz, procdump targeting lsass, nc -e, socat, chisel, rclone |
credential access / tunneling / exfil |
| Processes owned by root/SYSTEM that are normally user-level | privilege escalation |
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 · 90 lines · 45 tokens per session scan E aa09fd0e1fca
host-forensics is a skill published in the GitHub repository gensecaihq/Wazuh-Autopilot (57 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 1,349 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it E with 3 findings (reaches for credential files, downloads and executes remote code, 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-performance-optimizer
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer.
agent-refinement
Agent skill for refinement - invoke with $agent-refinement.
diag-harness
Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.
building-detection-rule-with-splunk-spl
Build effective detection rules using Splunk Search Processing Language (SPL) correlation searches to identify security threats in SOC environments.
nio-scan
Nio code/skill execution-risk scanner. Use when the user wants to scan a file, repo, directory, or skill for execution risks — e.g. "scan this code for risks", "is this file/plugin dangerous", "check this repo for malicious code", "run nio scan on ". Focused single-purpose skill; for other Nio operations use /nio.
nio-doctor
Nio config validator + connectivity check. Use when the user wants to validate their Nio setup — e.g. "run nio doctor", "is my nio config valid / working", "test my OAuth / external endpoint / LLM connectivity", "why isn't my scorer firing". Focused single-purpose skill; for other Nio operations use /nio.