preview-import
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to construct and execute shell commands (e.g.,
aem up --html-folder {dirPath}) using variables derived from an external JSON file (metadata.json). - Ingestion points: The skill reads
paths.dirPathandpaths.documentPathfrommetadata.jsonlocated in the local environment. - Boundary markers: No explicit boundary markers or validation instructions are provided to ensure the metadata values do not contain malicious shell metacharacters.
- Capability inventory: The skill utilizes the
aemCLI tool to start a local development server and serve files from paths defined in the metadata. - Sanitization: The instructions do not include steps to sanitize or validate the paths retrieved from the JSON file before using them in the command line interface.
Audit Metadata