sites
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data (such as trip options, prices, and routes) to generate structured web content. This creates a surface for indirect prompt injection where instructions embedded in the processed data could influence agent behavior.
- Ingestion points: User requests, trip options, product comparisons, and meal plans mentioned in the proactive creation section (SKILL.md).
- Boundary markers: None explicitly defined within the instructions.
- Capability inventory: Invokes site creation and deployment tools like
create_siteandcreate_and_deploy_basic_site(SKILL.md). - Sanitization: No sanitization or validation logic is specified in this file.
Audit Metadata