Food Delivery
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from third-party delivery platforms through browser automation, creating a surface for indirect prompt injection.
- Ingestion points: Restaurant names, menu descriptions, and platform-specific promotional content retrieved during the browsing and ordering process in
ordering.md. - Boundary markers: Absent. The instructions do not define delimiters or specific warnings to ignore instructions embedded in the website data.
- Capability inventory: The skill has capabilities including reading/writing local preference files and performing browser automation to navigate and place orders.
- Sanitization: No sanitization or validation of the data scraped from delivery platforms is specified before it is processed by the agent.
Audit Metadata