israeli-product-price-comparator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external websites (Zap, KSP, Ivory, etc.) via the WebFetch tool.
- Ingestion points: Web pages fetched from various Israeli retailers and comparison engines described in SKILL.md and SKILL_HE.md.
- Boundary markers: While the skill provides output templates, it does not define specific delimiters to isolate untrusted external content.
- Capability inventory: The skill is restricted to using the WebFetch tool and does not have access to high-risk tools like shell execution or file system modification.
- Sanitization: No explicit sanitization or filtering is implemented for the data retrieved from external URLs.
- [SAFE]: A deterministic detector flagged instructions regarding the avoidance of fabricating data (e.g., "Never fabricate a price to fill a gap") as a concealment pattern. However, analysis confirms these are benign accuracy guardrails intended to prevent the agent from providing unreliable information to the user.
Audit Metadata