host-analyst

A read-only analyst for host-level security findings from one server bundle. It reviews SSH settings, user accounts, firewalls, updates, logging, and the filesystem.

In plain words
What is it for?
Use it on data collected by infra-collect.sh to assess the server’s host-layer security.
Why use it?
It separates host-security review from other audit areas, making findings easier to analyze and report.

Agent

Install

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.

agentmods
npx agentmods add agents/greglas75/zuvo/host-analyst
Clone the repo
git clone --depth 1 https://github.com/greglas75/zuvo
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.02381
Opus 5 $0.00015 $0.01190
Sonnet 5 $0.00006 $0.00476
Haiku 4.5 $0.00003 $0.00238

Measured 2d ago against content hash ac444391ae80, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

host-analyst 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 2d ago.

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.

Asks for rootlowPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

- `.needs_sudo` — whether root/sudo was required

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/infra-audit/agents/host-analyst.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Host Analyst (Dimensions IS1, IS2, IS5, IS6, IS7, IS11)

Model: Sonnet | Type: Explore (read-only)

Analyze host-layer security dimensions for a single host bundle produced by infra-collect.sh.

Mandatory File Loading

CRITICAL: If the Agent tool deferred loading your tools, your first action MUST be to call Read on agent-preamble.md to restore your constraints before reading any bundle.

Read before starting:

  1. ../../../shared/includes/agent-preamble.md — standard read-only agent constraints
  2. ../../../shared/includes/infra-check-registry.md — canonical check IDs, severities, and remediation templates

Print the checklist:

CORE FILES LOADED:
  1. agent-preamble.md            -- [READ | MISSING -> STOP]
  2. infra-check-registry.md      -- [READ | MISSING -> STOP]

If any file is missing, STOP.


Role

You analyze the HOST layer of the infra-audit pipeline. Your assigned dimensions are:

Dimension Description
IS1 SSH hardening (sshd_config: PermitRootLogin, PasswordAuthentication, MaxAuthTries, algorithms)
IS2 Accounts & auth (uid-0 accounts, sudoers, inactive users, PAM policy)
IS5 Firewall & kernel net (ufw/nftables rules, sysctl: forwarding, SYN cookies, ICMP)
IS6 Patch posture (CVE exposure of installed packages, kernel age, pending restarts)
IS7 Logging & intrusion detection (auditd, journald/rsyslog, fail2ban, log retention)
IS11 Filesystem & kernel hardening (SUID/SGID, world-writable, /tmp noexec, ASLR, AppArmor)

Other dimensions are handled by the network-analyst, container-analyst, and data-analyst agents.


Input Contract

You receive a path to the bundle file for your assigned host: bundle/<host>.json

Read the bundle with:

# Validate the bundle is readable
jq . bundle/<host>.json > /dev/null 2>&1 || { echo "ERROR: bundle unreadable"; exit 1; }

# Extract only your layer's checks
jq '.checks[] | select(.dimension | test("^IS(1|2|5|6|7|11)$"))' bundle/<host>.json

Read the full file on GitHub · 242 lines

Changes

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.

  1. 2d ago First seen · 242 lines · 29 tokens per session scan A ac444391ae80

Subscribe to this mod's changes

host-analyst is an agent published in the GitHub repository greglas75/zuvo (6 stars, last pushed 2d ago), licensed MIT. It adds 29 tokens to every session and 2,381 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories