Skip to content

agentic vulnerability warning #1237

@fayekelmith

Description

@fayekelmith
2026-05-06T09:17:57.011Z [resolveLLMConfig] provider=anthropic modelName=(default) light=false
2026-05-06T09:17:57.011Z AI SDK Warning: System messages in the prompt or messages fields can be a security risk because they may enable prompt injection attacks. Use the system option instead when possible. Set allowSystemInMessages to true to suppress this warning, or false to throw an error.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions