What it is
An agent credential vault stores the keys and tokens AI agents use to reach other systems, so agents act with scoped, revocable access instead of hard-coded secrets. It encrypts secrets, rotates keys, enforces least-privilege scopes, and logs every access, keeping credentials out of prompts, flows, and agent configurations.
Why it matters
As agents gain more autonomy to take real-world actions, poorly managed credentials become a top attack surface. A vault reduces the risk of privilege-compromise and identity-spoofing incidents that could expose customer data.
Key components
- secret rotation
- least-privilege scoping
- access logging
- encrypted storage
How it connects
In Salesforce, Named Credentials and External Credentials play this role for callouts, so admins can scope, rotate, and audit the access each agent action uses.
Good to know
Review vault access logs alongside agent telemetry regularly — unused or over-scoped credentials are common findings in security audits.
Related terms
BYOK (Bring Your Own Key)
A model where users provide their own API keys for AI services (like OpenAI, Anthropic, or other LLM providers) instead of relying on the platform's bundled AI.
Identity Spoofing
Attacks where an adversary pretends to be a trusted user, agent, or system in order to issue commands or access data the agent would otherwise refuse.
OAuth 2.0
The authorization framework (RFC 6749) that lets an application act on a user’s behalf with a scoped access token instead of the user’s password.
Privilege Compromise
When an AI agent has been granted broader access than its task actually requires, every other vulnerability becomes more damaging — and the gap is usually a misconfiguration, not an attack.
