shopify-research
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs a helper script
scripts/crawlora.shto perform API calls. This script usescurlto send requests to the Crawlora service and handles data encoding safely. - [EXTERNAL_DOWNLOADS]: The skill communicates with
api.crawlora.netto retrieve Shopify storefront data. This is the official API endpoint for the service and belongs to the skill's author. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it ingests untrusted data (such as product descriptions and page content) from external Shopify stores. Evidence Chain:
- Ingestion points: Shopify product and page data fetched via
scripts/crawlora.sh. - Boundary markers: No explicit markers are used to delimit external content in the agent's context.
- Capability inventory: Shell command execution via the provided bash script.
- Sanitization: Documentation indicates that page body HTML is returned as 'cleaned text', which limits potential cross-site scripting or HTML-based injection vectors.
Audit Metadata