shoplazza-shop
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified. The skill's operations are aligned with its purpose as a store management tool.
- [COMMAND_EXECUTION]: The skill uses the
shoplazzaCLI to interact with store data. It includes safety practices like using--dry-runand requiring user confirmation for destructive operations. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes data from the store (e.g., metafields, analytics) which could contain malicious instructions. 1. Ingestion points: Commands that read store data such as
shop info get,shop analytics, andshop metafields listin SKILL.md and reference files. 2. Boundary markers: Not explicitly documented in these reference files. 3. Capability inventory: CLI commands for creating, updating, and deleting store resources as described in all files. 4. Sanitization: The skill relies on the CLI and the agent's safety protocols.
Audit Metadata