DIGGINGBEAGLE
Home/concepts

Topic · DiggingBeagle record

Model-controlled tool parameters

Any parameter an LLM can influence must be treated as untrusted input at the tool boundary.

Topic kind
pattern

Definition & limits

Frameworks can map natural-language output into structured function parameters. Validation must happen at the deterministic tool boundary because model-generated values can carry classic injection payloads.

Examples

  • Semantic Kernel filter interpolation.
  • MCP server parameters that become command and argument fields.

Research using this topic (1)

CaseSemantic Kernel prompt injection reached host code execution

Cite this record

DiggingBeagle. “Model-controlled tool parameters.” https://diggingbeagle.com/concepts/model-controlled-tool-parameters/

Citation guidance

Why this archive exists

The source matters after the headline fades.

DiggingBeagle is a non profit research project documenting AI security incidents, agent failures, vulnerabilities and AI-assisted operations. A case keeps its claims beside the sources that support, contest or limit them. Later updates stay visible, so a reader can see when the account changed.

We publish case reconstructions, dated reporting and analysis across records. Each has a different evidentiary role. About the project and our methodology explain how the work is reviewed.