Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add greglas75/zuvo/plugin install zuvoWrote 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/greglas75/zuvo/infra-audit)<a href="https://agentmods.dev/skills/greglas75/zuvo/infra-audit"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/infra-audit.svg" alt="Measured on agentmods" 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 | $0.00229 | $0.10126 |
| Opus 5 | $0.00114 | $0.05063 |
| Sonnet 5 | $0.00046 | $0.02025 |
| Haiku 4.5 | $0.00023 | $0.01013 |
Grade B, and why
infra-audit scanned grade B 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 6d 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.
4. **Privilege probe (E3 / §3):** `sudo -n true` → `privilege_mode` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
# ssh_key: ~/.ssh/id_ed25519 # optional (else ssh config/agent); path only — key never read Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| `--scan-via <ssh-target>` | Run the external leg FROM this SSH host via portable nc/openssl/curl (no nmap/testssl/nuclei/proxychains; **macOS-safe**; a real internet vantage). Highest external-vantage priority. Else ho How it starts
The opening of the file, as written. The whole thing — 722 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:infra-audit
Audit the security of LIVE servers/infrastructure the user owns, over SSH, plus external exposure verification through a proxy. This is the orthogonal companion to
security-audit(repo-resident IaC config),db-audit(DB as a data layer), andpentest(app-code exploitability). Routing boundary: "is my server secure?" → infra-audit.Architecture (DD-5): a deterministic collector (
scripts/infra-collect.sh) gathers everything per host into a normalized JSON bundle; parallel LLM analysts each see only their layer's normalized findings; deterministic dedup/scoring/report assembly. The LLM interprets, never detects.
Argument Parsing
| Argument | Meaning |
|---|---|
[path/to/hosts.yaml] |
Fleet audit from inventory (default: zuvo/infra/hosts.yaml if present) |
--host user@addr[:port] |
Single ad-hoc host, no inventory file needed |
--quick |
IS1 + IS3 (internal) + IS4 only; < 3 min/host target |
--dimensions IS1,IS3,… |
Explicit dimension subset |
--no-install |
Hard read-only: never offer tool installation (disables the DD-3 gate) |
--dry-run |
Print every SSH/local command without executing; no connections beyond DNS |
--resume <run-dir> |
Continue an interrupted run from state.json |
--proxy <url> |
External-scan proxy override (else hosts.yaml defaults.proxy, else $ZUVO_SCAN_PROXY) |
--scan-via <ssh-target> |
Run the external leg FROM this SSH host via portable nc/openssl/curl (no nmap/testssl/nuclei/proxychains; macOS-safe; a real internet vantage). Highest external-vantage priority. Else hosts.yaml defaults.scan_via, else $ZUVO_SCAN_VIA |
--external direct |
Explicit opt-in to a proxyless external scan (polite timing -T2 --max-rate 50) |
--skip-external |
Internal vantage only (no external leg) |
--deep-scan |
nmap -p- instead of --top-ports 1000 (EXCLUDED from the AC-S2 timing SLA + 30-min wall clock) |
--confirm-targets <sha256> |
Non-interactive authorization: sha256 of the resolved target list printed by a prior --dry-run. REQUIRED for any non-interactive run — without it the run ABORTS at the gate (targets are never auto-approved) |
What ships with it
4 files 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.
- 6d ago First seen · 722 lines · 229 tokens per session scan B 8352046a1412
infra-audit is a skill published in the GitHub repository greglas75/zuvo (6 stars, last pushed yesterday), licensed MIT. It adds 229 tokens to every session and 10,126 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
kanso-prompting
Use when rewriting, sharpening, or producing a prompt for Claude or another current frontier model. Sets standing rules for getting better LLM output through better prompts. Loaded by /kanso-task; not directly invoked by the user.
ring:adopting-lib-commons-huma-wrapper
Adopting the lib-commons/v5 shared Huma (OAS 3.1) OpenAPI wrapper + RFC 9457 problem model (commons/net/http/{openapi,problem}) in a Lerian Go service: wire openapi.New/ServeSpec + problem.Install (central >=500 scrub) on BOTH runtime and spec-gen paths, the per-rail problem.MapError flex seam, and rename-only spec…
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
ring:engineering-prompts
Expert prompt engineering and optimization for LLMs and AI systems. Covers core patterns (zero-shot, few-shot, CoT, role-playing, constitutional, tree-of-thoughts), common use cases, and a three-phase process. Use when crafting or optimizing prompts for AI systems. Skip when the prompt is trivial or already performing…
composer-prompting
Internal guidance for shaping a well-specified coding task into a tight Cursor/Composer prompt before delegating it via /cursor:delegate.
debt-ops-init
Write or refresh a "Tech debt operations" section in the project's AGENTS.md so the team shares one source of truth for debt-ops disciplines. Run ONLY when the user explicitly asks to set up, install, or initialize debt-ops disciplines — never auto-invoke. Idempotent; only the managed section changes, other sections…