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 capitalone/VulnHunter --skill vulnhuntgit clone --depth 1 https://github.com/capitalone/VulnHunterWrote 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/capitalone/vulnhunter/vulnhunt)<a href="https://agentmods.dev/skills/capitalone/vulnhunter/vulnhunt"><img src="https://agentmods.dev/badge/skills/capitalone/vulnhunter/vulnhunt/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/capitalone/vulnhunter/vulnhunt"><img src="https://agentmods.dev/badge/skills/capitalone/vulnhunter/vulnhunt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.04862 |
| Opus 5 | $0.00021 | $0.02431 |
| Sonnet 5 | $0.00008 | $0.00972 |
| Haiku 4.5 | $0.00004 | $0.00486 |
Grade A, and why
vulnhunt 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 9d 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.
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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VulnHunter Security Audit Skill
MANDATORY FIRST ACTIONS
Step 0: Model check (interactive/direct invocation only). When invoked interactively — i.e. path B below, with no "Pre-resolved scan metadata" block — inspect the model you are running as. If it is NOT Opus 4.7 or higher, STOP immediately and tell the user (do not run any tools, resolve the target, or offer the mode menu yet):
⚠️ VulnHunter is optimized for Claude Opus 4.7/4.8 and may be unreliable on other models. Please switch with the
/model opuscommand, then re-run/vulnhunt.
Wait for the user. Only proceed past this step once they are on Opus, or if they explicitly reply that they want to continue on the current model anyway.
Skip this check under path A (agent-driven); the agent controls the model.
Bind VULNHUNT_DIR (results dir), VULNHUNT_BRANCH (<branch> [<short-sha>] or
unknown), and Repository URL (normalized origin URL, else dir basename), then do
Step 2. Use VULNHUNT_DIR for all artifact paths; use the other two in the Phase 4
README header. Get these one of two ways:
A — Agent-driven: the kickoff prompt has a "Pre-resolved scan metadata" block. Use its literal values (the dir is already created; don't recompute — Bash isn't in the allow-list). Its Bash line drives Step 2: "NOT available" → read-only; "AVAILABLE" → install.
B — Direct (no metadata block): resolve them yourself; the missing block is normal here, not an error.
- Target: the current directory, unless the invocation names a path. Confirm in one line.
- Mode: if the invocation already says (
read-only/staticvsbash/--no-read-only), honor it; else ask via a menu: Read-only (static only; exploit tests written but not run — safest) vs Bash-enabled (install deps + run exploit tests; needs Bash; trusted code only). Don't start Phase 1 until resolved. - Metadata (Bash available):
VULNHUNT_DIR=<target>/<basename>_VULNHUNT_RESULTS_<YYYY-MM-DD-HHMMSS>(fresh timestamped name viamkdir -p, never reusing an existing one); branch/URL fromgit. No Bash: ask the user to enable it or supply a pre-made dir path + branch/URL.
What ships with it
12 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.
- phases/phase1_recon.md 28 KB
- phases/phase2_class_inj.md 10 KB
- phases/phase2_class_log.md 8.1 KB
- phases/phase2_class_nav.md 13 KB
- phases/phase2_hunt.md 13 KB
- phases/phase2_shared.md 21 KB
- phases/phase2b_verify.md 16 KB
- phases/phase3_reproduce_test.md 12 KB
- phases/phase3c_fixes.md 3.5 KB
- phases/phase3d_sweep.md 7.1 KB
- phases/phase4_report.md 9.0 KB
- README.md 3.6 KB
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.
- 9d ago First seen · 353 lines · 42 tokens per session scan A 02e3704cedf5
vulnhunt is a skill published in the GitHub repository capitalone/VulnHunter (984 stars, last pushed 24d ago), licensed Apache-2.0. It adds 42 tokens to every session and 4,862 once invoked, about $0.0002 per session on Opus 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 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.