Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Vault Secrets Skill — measured AI agent skill | DecimalAI

automateyournetwork/vault-secrets

NewSkillScoreMaintained

Manage HashiCorp Vault KV secrets with strict value protection.

Securityby automateyournetwork

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Security & AppSec pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/automateyournetwork-vault-secrets/SKILL.md

decimalai skills pull automateyournetwork-vault-secrets --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/automateyournetwork-vault-secrets/SKILL.md https://app.decimal.ai/s/automateyournetwork-vault-secrets/SKILL.md

Raw file: /s/automateyournetwork-vault-secrets/SKILL.md ↗ · machine-readable summary at /s/automateyournetwork-vault-secrets.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-26% tokens0% turns45% of whole cases pass with skill (10/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	14%	0%
case-05	✗→✓	▲ Improved	-25%	0%
case-08	✗→✓	▲ Improved	-8%	0%
case-16	✗→✓	▲ Improved	-47%	0%
case-17	✗→✓	▲ Improved	-28%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

automateyournetwork / netclaw

workspace/skills/vault-secrets/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

Vault Secrets Skill

Manage HashiCorp Vault KV secrets with strict value protection.

Tools

| Tool | Description | |------|-------------| | read_secret | Read secret metadata (values NEVER displayed) | | write_secret | Write secret to KV engine | | list_secrets | List secrets in a path | | delete_secret | Delete a secret | | get_secret_metadata | Get secret version metadata | | inject_secret | Inject secret value to integration |

CRITICAL: Secret Value Protection

Secret values are NEVER displayed in responses. When reading secrets:

Only metadata is shown (version, created time, etc.)
Actual secret values are never logged or returned
Use inject_to parameter to send secrets directly to integrations

Example Queries

List secrets in the network-devices path

Read metadata for secret network-devices/router-creds

Inject router credentials to pyATS testbed

Write a new secret to network-devices/switch-01

Prerequisites

VAULT_ADDR Vault server address
VAULT_TOKEN Authentication token with appropriate policy
Optional: VAULT_NAMESPACE for Vault Enterprise

Server

This skill uses the vault-mcp server which connects to Vault API.

Want to see if automateyournetwork/vault-secrets would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.