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 vectra-ai-research/vectra-soc-agent-starter --skill virustotalgit clone --depth 1 https://github.com/vectra-ai-research/vectra-soc-agent-starterWrote 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/vectra-ai-research/vectra-soc-agent-starter/virustotal)<a href="https://agentmods.dev/skills/vectra-ai-research/vectra-soc-agent-starter/virustotal"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/virustotal/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/vectra-ai-research/vectra-soc-agent-starter/virustotal"><img src="https://agentmods.dev/badge/skills/vectra-ai-research/vectra-soc-agent-starter/virustotal.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 | $0.00182 | $0.04221 |
| Opus 5 | $0.00091 | $0.02110 |
| Sonnet 5 | $0.00036 | $0.00844 |
| Haiku 4.5 | $0.00018 | $0.00422 |
Grade A, and why
virustotal 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 12d 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.
description: Enriches Vectra findings with VirusTotal threat intelligence — IOC reputation lookup for IPs, domains, URLs, and file hashes via the VirusTotal v3 API. Ships two paths — a standalone Bash CLI (scripts/vt-loo How it starts
The opening of the file, as written. The whole thing — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
VirusTotal — IOC Lookup & TI Enrichment
This skill wires the agent into the VirusTotal v3 API for IOC
enrichment. It ships a Bash adapter (scripts/virustotal.sh) that exposes
a single function — virustotal_enrich — designed to be sourced by a
host IOC-enrichment workflow (the agent's outer set -euo pipefail Bash
runner that loops over a list of IOCs and dispatches per-IOC to multiple
intel sources).
The adapter handles: API-key presence check → IOC-type guard →
type-specific URL construction (file hash / IP / domain / URL) →
authenticated GET → JSON parse → normalized result emission with a
compact one-line summary.
Use this skill when
- The user pastes an IOC (IPv4 / IPv6, domain, URL, file hash) and asks "is it known bad?" / "look it up in VirusTotal".
- A
vectra-investigatorplaybook-<category>.mdlands a TP-leaning verdict and the analyst wants external corroboration before escalating. - A
vectra-huntTI-driven hunt produces hits whose IOCs need reputation context for the final report. - You're building or running a multi-source IOC-enrichment workflow that sources this adapter alongside other vendor adapters (the function is drop-in compatible with any framework that provides the helper contract documented below).
Do not use this skill to:
- Override Vectra's behavioral verdict — reputation does not make a TP into a BTP or vice versa.
- Hunt across the Vectra tenant — that's
vectra-hunt. - Triage a Vectra detection end-to-end — that's
vectra-investigator(which loads the matchingplaybook-<category>.md).
Prerequisites
| Requirement | Notes |
|---|---|
| VirusTotal API key | Public (free, low rate) or Premium. Exposed to the adapter as the VT_API_KEY environment variable. Never hard-code the key in scripts or commit it. |
curl |
Used by the host framework's adapter_fetch_json_or_error. |
jq |
Used inline for response summarization. |
base64 |
Required only for URL IOCs (VirusTotal expects URL IOCs as URL-safe base64 of the canonical URL). The adapter degrades gracefully and emits a base64 utility missing error if absent. |
| Bash 4+ | [[ ]], arrays, local declarations. |
| Host workflow framework | The adapter calls helper functions (see "Framework contract" below). It does not stand alone. |
What ships with it
2 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.
- 12d ago First seen · 350 lines · 182 tokens per session scan A 099a9dbf2ec0
virustotal is a skill published in the GitHub repository vectra-ai-research/vectra-soc-agent-starter (2 stars, last pushed 4d ago), licensed MIT. It adds 182 tokens to every session and 4,221 once invoked, about $0.0009 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…