component-wiring-check
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: In SKILL.md, the skill instructs the agent to execute shell commands such as 'dxs configuration get' and 'jq' for read-only auditing of component configurations. These tools are project-specific utilities for the Datex Studio environment.
- [PROMPT_INJECTION]: In SKILL.md, the skill identifies a surface for indirect prompt injection by processing external JSON configuration files. (1) Ingestion points: JSON output files generated by the 'dxs configuration get' command. (2) Boundary markers: The instructions do not specify the use of delimiters or 'ignore' warnings for the ingested configuration content. (3) Capability inventory: The skill's capabilities are limited to executing the 'dxs' and 'jq' tools; it explicitly forbids the use of mutation commands like 'dxs configuration upsert'. (4) Sanitization: No specific sanitization or validation of the ingested JSON structure is mentioned prior to the audit logic.
Audit Metadata