skills/datex/skills/storage-creator/Gen Agent Trust Hub

storage-creator

Pass

Audited by Gen Agent Trust Hub on Aug 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the dxs CLI and jq utility to perform operations on storage configuration files, including fetching, validating, and upserting data to the platform. This behavior is consistent with the tool's intended use for developer workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill generates JSON configurations from natural language requirements, which presents a surface for indirect prompt injection. However, this is a primary feature of the tool and the resulting configuration is subject to platform-level validation.
  • Ingestion points: Requirements brief from the conversation context (SKILL.md).
  • Boundary markers: No explicit delimiters or boundary instructions are specified.
  • Capability inventory: File system writing via jq and cloud configuration updates via the dxs CLI.
  • Sanitization: Not explicitly specified in the instructions, but the platform CLI performs schema validation before updates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 20, 2026, 01:11 PM
Security Audit — agent-trust-hub — storage-creator