Critical-risk tools in Tuning Engines - LLM Fine-Tuning

Critical severity Tuning Engines - LLM Fine-Tuning MCP Server 7 of 73 tools

7 of the 73 tools in Tuning Engines - LLM Fine-Tuning are classified as critical risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.

Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.

Tools at critical risk

cancel_evaluation Destructive

Cancel a running or queued evaluation.
cancel_job Destructive

Cancel a running or queued fine-tuning job. The job will be charged for any GPU time already used.
delete_dataset Destructive

Delete a dataset from the platform.
delete_model Destructive

Delete a trained model from cloud storage.
tenant_invitation_cancel Destructive

Cancel a pending tenant invitation. Requires tenant owner/admin API token.
tenant_resource_delete Destructive

Delete or revoke an allowlisted tenant resource. Requires tenant owner/admin API token.
tenant_team_remove Destructive

Remove a tenant member. Requires tenant owner/admin API token.

Attacks that target this class

Critical-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.

Destructive Action Autonomy
Privilege escalation via admin-only tools
Data exfiltration via tool chaining
Runaway Tool Loops

Critical-risk tools in Tuning Engines - LLM Fine-Tuning

Tools at critical risk

Attacks that target this class

More on Tuning Engines - LLM Fine-Tuning

Enforce policy on every Tuning Engines - LLM Fine-Tuning tool call.