Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/greglas75/zuvonpx agentmods add skills/greglas75/zuvo/pentestWrote 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/pentest)<a href="https://agentmods.dev/skills/greglas75/zuvo/pentest"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/pentest/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/greglas75/zuvo/pentest"><img src="https://agentmods.dev/badge/skills/greglas75/zuvo/pentest.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 857 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00124 | $0.11159 |
| Opus 5.5 | $0.00050 | $0.04464 |
| Sonnet 5.5 | $0.00025 | $0.02232 |
| Haiku 4.5 | $0.00012 | $0.01116 |
Grade A, and why
pentest 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
which curl 2>/dev/null && echo "curl: OK" || echo "curl: MISSING" How it starts
The opening of the file, as written. The whole thing — 896 lines — stays where its author put it; the contents beside it link to each section on GitHub.
zuvo:pentest -- Hybrid Penetration Testing
White-box source-to-sink analysis combined with optional black-box runtime verification. zuvo:pentest is stack-aware: it selects sources, sinks, framework-safe patterns, and CodeSift recipes based on the detected project stack before dispatching any agents. Findings are built from a deterministic candidate schema, then merged with canonical-key deduplication and centralized scoring.
When to use: Before releases, after zuvo:security-audit flags issues that need exploit verification, testing CMS installations, verifying security fixes.
Out of scope: Static code quality (use zuvo:code-audit), broad security posture review (use zuvo:security-audit), API contract audit (use zuvo:api-audit).
Argument Parsing
| Argument | Effect |
|---|---|
[path] |
Limit analysis to a specific directory |
--url <url> |
Target URL for runtime probes (enables hybrid mode) |
--from-audit <dir> |
VERIFICATION mode -- verify PT/SEC findings from a prior audit directory |
--cms joomla|wordpress|drupal |
Force-enable CMS overlay |
--quick |
PT1 + PT3 + PT4 only (critical gates), no live probing |
--scope <path> |
Alias for [path] |
--dimensions PT1,PT2 |
Audit only specified dimensions |
--verify-live |
Enable Phase 3 exploit verification against a running app |
--rate <N> |
Requests per second cap (default: 5) |
--source |
Force white-box track only -- skip live probes even if --url present |
--runtime |
Force black-box track only -- skip source analysis. Requires --url. |
--strict-v2 |
Count the 14 v2 vuln classes toward score caps / critical-gate totals — the 11 original (incl. both GraphQL classes) plus header_injection, token_compare_bypass, weak_credential_storage added 2026-08-01. Default: warning-only grace — identical spec to security-audit's "v2 class grace" section, and the graced set is all 14, not the original 11: a class added to v2 is a v2 class, and gracing 11 of 14 would silently enforce the three newest on day one. Warning-only through the 1.4.x window, full weight in 1.5.0; v2 findings are still reported, excluded only from gate totals (a CRITICAL or HIGH one is recorded through backlog-add like any other: 7.5); identical v2-grace: warning-only (N v2 findings reported, excluded from gate; --strict-v2 to enforce) line. |
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.
- 2d ago Changed · +10 lines aa8598863504
- 1mo ago Changed · -2 lines 7cb37bd989e7
- 1mo ago First seen · 888 lines · 124 tokens per session scan A f1a51eeee6f1
pentest is a skill published in the GitHub repository greglas75/zuvo (8 stars, last pushed today), licensed MIT. It adds 124 tokens to every session and 11,159 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
ai-agent-bench
Compare Claude Code and Codex on the same code task, with isolated worktrees, common checks, time, and cost.
create-test
Define or implement regression proof: test strategy, black-box or integration tests, KPIs, thresholds, audits, or missing tests.
wrap-up-branch
Finish a feature branch: add missing tests, review and fix the code, align docs, then merge only after explicit confirmation.
eval-regression
Check skill routing or behavior, investigate a regression, or compare plugin changes with a base commit.
brooks-health
Combined codebase health dashboard that scores a project across all four quality dimensions — PR quality, architecture, tech debt, and test quality — in a single pass, drawing on twelve classic engineering books. Triggers when: user wants an overall quality assessment, asks "how healthy is this codebase?", "run all…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…