israeli-ecommerce-compliance
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves scanning and analyzing content from external websites, which creates a potential surface for indirect prompt injection if the scanned websites contain malicious instructions intended to manipulate the agent's behavior.
- Ingestion points: External website content is ingested via the
WebFetchtool and browser automation as described in the audit steps for accessibility and cookie consent inSKILL.mdandSKILL_HE.md. - Boundary markers: The skill's instructions do not include specific delimiters or guidelines to help the agent distinguish between the skill's instructions and potentially malicious content found within the fetched HTML.
- Capability inventory: The skill has access to
Bash(python:*)andWebFetchto perform its website audits and data processing tasks. - Sanitization: There are no defined processes for sanitizing, filtering, or escaping the external content retrieved from websites before it is processed and interpreted by the AI agent.
Audit Metadata