israeli-product-price-comparator

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of legitimate instructions for assisting users with product price comparisons in Israel. It references well-known and reputable Israeli retailers (such as Zap, KSP, and iDigital) and government resources for customs information.
  • [INDIRECT_PROMPT_INJECTION]: The skill contains an indirect prompt injection surface because its primary function involves fetching and processing data from external websites.
  • Ingestion points: Data is ingested from third-party price comparison sites and retailer web pages (e.g., zap.co.il, ksp.co.il) using the WebFetch tool.
  • Boundary markers: The instructions do not specify the use of delimiters or provide explicit warnings to the agent to ignore potential instructions embedded within the external HTML or product descriptions.
  • Capability inventory: The skill environment permits the use of Bash(node:*), Bash(python:*), and WebFetch, which could potentially be abused if an attacker successfully injects commands into a product page being scanned.
  • Sanitization: No specific sanitization or validation logic is defined for the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 09:15 PM
Security Audit — agent-trust-hub — israeli-product-price-comparator