How to meet it
OWASP AISVS v1.01
Orchestration & Agentic Security · Agent Authorization, Delegation, and Continuous Enforcement
Keep secrets out of the model's context
Verify that secrets and credentials required by an agent at runtime are not exposed within the model's observable context, including the context window, system prompts, or tool call parameters.
OWASP AISVS v1.01, requirement 9.5.4
In plain English
Keep secrets out of anything the model can see: the context window, system prompt and tool call parameters.
What good looks like
- Credentials are added by the tool runtime after the model's call.
- Prompts and tool arguments contain no secrets.
- Logs are checked for leaked secrets.
How teams usually do it
- Tool gateways that inject credentials server side.
- Secret scanning on prompts and logs.
Evidence an auditor would accept
- Tool call design and scan results.
Common mistakes
- Putting an API key in the system prompt so the agent can "use it".
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.