managing-tilebox-datasets

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for utilizing the tilebox CLI to perform administrative and operational tasks on datasets. These commands are consistent with the vendor's own tools and services.
  • [PROMPT_INJECTION]: Indirect prompt injection risk was evaluated as the skill processes data from external datasets. 1. Ingestion points: Data retrieved through tilebox dataset query, tilebox dataset find, and metadata from tilebox dataset get. 2. Boundary markers: The skill does not define explicit delimiters or instructions to disregard potential commands within dataset content. 3. Capability inventory: The skill has the capability to create, update, and delete datasets and collections, and to perform spatiotemporal queries. 4. Sanitization: No specific sanitization or validation of retrieved dataset content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:01 PM
Security Audit — agent-trust-hub — managing-tilebox-datasets