ai-shopping-readiness-ecommerce
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data including rendered HTML, structured data feeds, and policy pages from third-party e-commerce sites. This represents a surface for indirect prompt injection, as malicious instructions could be embedded in the site content to influence the agent's analysis or behavior.
- Ingestion points: Rendered HTML, product feeds, and policy pages from external URLs (SKILL.md).
- Boundary markers: The instructions do not mandate the use of delimiters or include warnings to ignore instructions found within the processed external data.
- Capability inventory: The skill is limited to data analysis and reporting; it does not contain scripts or commands for file writing, system modification, or network exfiltration beyond the intended analysis scope.
- Sanitization: No sanitization or input validation logic is described for the external content being processed.
Audit Metadata