Skip to main content
Agent skill

Vanta

Read a team's Vanta compliance posture: failing tests and vulnerabilities, and what to remediate for SOC 2, ISO 27001 or HIPAA.

Get started

Get the complete skill folder, including its scripts and reference files.

When to use this skill

Use Vanta when an AI agent needs a reusable SKILL.md workflow for this job: Read a team's Vanta compliance posture: failing tests and vulnerabilities, and what to remediate for SOC 2, ISO 27001 or HIPAA.

When not to use it

Skip Vanta when the task is outside the coding category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.

How to install

Where will you use it?

Install scope
Claude Code folder setup
mkdir -p ~/.claude/skills/vanta
# Save SKILL.md to ~/.claude/skills/vanta/SKILL.md
  1. Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/vanta/SKILL.md. For a shared project, commit the folder at .claude/skills/vanta/ instead.
  2. Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
  3. For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.

Full install guide for Claude, Cursor, and Codex →

Try a starter prompt

After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.

Starter prompt
Use the Vanta skill for this task: Use Vanta when this documented workflow matches the task. Confirm any required inputs or files before making changes.

What supports this recommendation?

69/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.

Documentation
73/100
Practical detail
68/100
Source evidence
63/100
Source signals
70/100
Model compatibility evidence
  • claudeuntested

    No model-specific signal or recorded compatibility test was found.

  • chatgptuntested

    No model-specific signal or recorded compatibility test was found.

  • geminiuntested

    No model-specific signal or recorded compatibility test was found.

  • copilotuntested

    No model-specific signal or recorded compatibility test was found.

  • llamauntested

    No model-specific signal or recorded compatibility test was found.

  • perplexityuntested

    No model-specific signal or recorded compatibility test was found.

  • mistraluntested

    No model-specific signal or recorded compatibility test was found.

  • grokuntested

    No model-specific signal or recorded compatibility test was found.

Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.

What this skill does

# Vanta compliance

Use this skill when the user wants to know which compliance checks are failing or what infrastructure issues need to be resolved for their security frameworks (SOC 2, ISO 27001, HIPAA, PCI, GDPR) as tracked by Vanta.

The Vanta access token is held **server-side** by Nuphos. You never handle it — read everything through the Nuphos API with `ac`. Do not ask the user for a Vanta token, and do not paste tokens into chat.

## Discovering the integration

The enabled credentials prompt lists each Vanta integration with its `integrationId` and a `testsEndpoint`. If none is listed, ask the user to bind a Vanta integration and enable it for this session — do not conclude Vanta is unsupported.

## Reading failing tests (the issues to fix)

Each Vanta *test* is one compliance check. The list route wraps results in an object, so extract `.tests[]` before piping to `jq`:

```bash # Default: tests that NEED ATTENTION (the compliance issues to resolve) ac /teams/<teamId>/vanta-integrations/<integrationId>/tests # -> { "tests": [...] }

# Only infrastructure-facing categories (Infrastructure, Vulnerability # management, Logging, Monitoring & alerts, Data storage): ac "/teams/<teamId>/vanta-integrations/<integrationId>/tests?infraOnly=true"

# Change the status filter (e.g. PASSED, DEACTIVATED): ac "/teams/<teamId>/vanta-integrations/<integrationId>/tests?status=PASSED" ```

Each test carries everything needed to explain and remediate the issue:

```bash ac "/teams/<teamId>/vanta-integrations/<integrationId>/tests?infraOnly=true" \ | jq -r '.tests[] | "[\(.category)] \(.name)\n why: \(.failureDescription)\n fix: \(.remediationDescription)\n"' ```

Fields: `id`, `name`, `category`, `status`, `failureDescription`, `remediationDescription`, `lastTestRunDate`.

## How to help

- Summarize failing tests grouped by category; lead with Infrastructure and Vulnerability management when the user is asking about infra. - For each issue, use `failureDescription` to explain what's wrong and `remediationDescription` for how to fix it. - When a failing test maps to a resource you can act on through another bound provider (e.g. a Cloudflare setting, an AWS config, a GitHub vulnerability), offer to remediate it there — but confirm with the user before any change.

## Safety

- Read-only. This skill only reads compliance status; it never writes to Vanta. - Never print or echo the Vanta token (it is not exposed to the sandbox by default — reads go through the Nuphos API above).

Intended uses

  • Use Vanta when this documented workflow matches the task.

Implementation notes

  • Review the source instructions and adapt inputs before running the workflow.

Try it, then tell us how it went

A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.