booking-com-hotel-data

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the scavio library for Python and Node.js, as well as the requests library. These are standard dependencies for interacting with the vendor's API endpoints at api.scavio.dev.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes natural language hotel data and guest reviews from external sources, which presents a potential surface for indirect prompt injection attacks.
  • Ingestion points: Data is ingested through the /api/v1/booking/hotel and /api/v1/booking/reviews endpoints, which return property descriptions and user review text.
  • Boundary markers: The skill instructions do not specify any boundary markers or delimiters to separate the retrieved external content from the agent's internal prompt context.
  • Capability inventory: The skill allows the agent to make POST requests to an external API (api.scavio.dev) to retrieve information.
  • Sanitization: The provided documentation does not include details on sanitization, filtering, or validation mechanisms for the natural language data received from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 12:24 PM
Security Audit — agent-trust-hub — booking-com-hotel-data