travel-assistant
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of untrusted data from external websites, creating a surface for indirect prompt injection. * Ingestion points: External travel aggregator websites accessed via the 'WebFetch' tool as described in the 'Using WebFetch for Travel Research' section of SKILL.md. * Boundary markers: Absent. The skill does not provide delimiters or instructions for the agent to distinguish between its own instructions and content fetched from the web. * Capability inventory: The skill uses web scraping tools to retrieve and analyze prices, availability, and amenities from third-party sites. * Sanitization: Absent. There are no instructions to validate, filter, or escape content retrieved from external websites before processing.
Audit Metadata