wundervault-vault

Read passwords, API keys, and credentials from a Wundervault encrypted secret vault, and run vault-authorized shell commands with secrets injected — without exposing them in chat. Self-hosted alternative to 1Password or Bitwarden for agents. Requires the @wundervault/mcp-server npm package.

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "wundervault-vault" with this command: npx skills add snoweman/wundervault-vault

Wundervault Vault

Wundervault is an encrypted, self-hosted secret vault that exposes secrets to agents via MCP tools. Secrets never appear in chat — they are decrypted server-side and injected directly into commands or returned over the encrypted MCP channel.

Check Setup First

Before doing anything vault-related, check whether the vault tools are available:

  • vault_entries_list — available? → vault is connected, proceed
  • If tools are missing → tell the user to install the MCP server (see INSTALL.md)

Tools

vault_entries_list

List all vault entries available to this agent. Returns entry IDs and names only — no secret values.

vault_entries_list()
→ [{ id: "abc123", name: "ResendApiKey", tier: "full" }, ...]

Use this first to discover available secrets before calling vault_entry_get.

vault_entry_get

Retrieve a secret by entry ID. The plaintext value is returned over the encrypted MCP channel.

vault_entry_get(entry_id: "abc123")
→ { name: "ResendApiKey", value: "re_..." }

Use the entry ID from vault_entries_list, not the secret name.

vault_exec

Execute a shell command with a vault secret injected — the secret is never exposed in chat or logs.

vault_exec(entry_id: "abc123", command: "npm publish --access public")

Two tiers:

  • Tier 1 (free): runs immediately, no unlock needed
  • Tier 2 (session-locked): call vault_session_unlock first — used for high-risk operations (deployments, publishes, infrastructure changes)

Shell escape sequences ($(), backticks, bash -c, eval) are hard-blocked before the secret is decrypted. Do not attempt to use them.

vault_entry_inject_env

Write a secret into a config file as an environment variable, without it passing through chat.

vault_entry_inject_env(entry_id: "abc123", path: "/home/user/app/.env", key: "RESEND_API_KEY")

vault_session_unlock

Unlock Tier 2 execution for the current session. Call this before vault_exec on a Tier 2 entry.

vault_session_unlock()
→ { unlocked: true, expires_at: "..." }

vault_session_status

Check whether the current session is unlocked and when it expires.

vault_session_status()
→ { locked: false, expires_at: "..." }

vault_entry_forget

Discard a vault entry reference from context. Does not delete the vault entry.

vault_entry_forget(entry_id: "abc123")
→ ✔️ Reference discarded.

Common Patterns

Find and read a secret:

1. vault_entries_list() → get entry ID for "ResendApiKey"
2. vault_entry_get(entry_id: "abc123") → use value

Run a command with secret injected (Tier 1):

vault_exec(entry_id: "abc123", command: "aws s3 sync ./dist s3://mybucket")

Tier 2 flow (e.g. npm publish, deploy):

1. vault_session_unlock()
2. vault_exec(entry_id: "abc123", command: "npm publish --access public")

Security Notes

  • Secrets are end-to-end encrypted; the agent receives only what it needs
  • The inject_as field on vault entries controls how the secret is passed (env var name, CLI flag prefix, etc.)
  • Tier 2 entries are configured by the vault owner — the agent cannot escalate a Tier 1 entry to Tier 2
  • Never echo, log, or store a secret retrieved via vault_entry_get

More Info

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Security

ArmorClaw

AES-256 encrypted secrets manager for OpenClaw agents. Store API keys, tokens, and credentials in a secure local vault instead of plain-text .env files. Feat...

Registry SourceRecently Updated
1110Profile unavailable
General

bun-do

Manage bun-do tasks and projects — add tasks, edit tasks, delete tasks, toggle done, manage subtasks, and log project progress entries. Use when the user say...

Registry SourceRecently Updated
6630Profile unavailable
General

ClawRAG - Self-hosted RAG & Memory

Self-hosted RAG engine with hybrid semantic and keyword search, document ingestion, local privacy, and seamless OpenClaw integration via Docker.

Registry SourceRecently Updated
1.6K0Profile unavailable
Security

Privacy Mask

Mask, redact, anonymize and censor sensitive information (PII) in screenshots and images — phone numbers, emails, IDs, API keys, crypto wallets, credit cards...

Registry SourceRecently Updated
4611Profile unavailable