preview-import

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes 'aem up' to start a local development server for Adobe Experience Manager Edge Delivery Services. This is the intended behavior for the tool's primary purpose.
  • [Indirect Prompt Injection] (SAFE): The skill utilizes 'documentPath' from local 'metadata.json' files to construct URLs. 1. Ingestion points: metadata.json. 2. Boundary markers: Absent. 3. Capability inventory: Local file access and subprocess execution. 4. Sanitization: Absent. The risk is considered negligible as the operation is confined to a local development environment and standard project files.
  • [Data Exposure & Exfiltration] (SAFE): File access is limited to local project resources such as screenshots and HTML files. No patterns of sensitive data exfiltration or hardcoded credentials were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:30 PM