restaurant-recommendations
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process data from external sources such as restaurant menus, hours, and local reviews, which constitutes an ingestion surface for untrusted data.
- Ingestion points: External restaurant websites, menus, independent local coverage, and opinion pieces as specified in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the researched content.
- Capability inventory: The skill references external tool capabilities for food ordering (
$orbit:food-ordering) and restaurant booking ($orbit:restaurant-booking). - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external research sources.
Audit Metadata