happyhorse
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices by directing users to use the platform's secure configuration for API tokens instead of requesting them within the conversation.
- [INDIRECT_PROMPT_INJECTION]: The skill includes an inherent attack surface for tools that process external data from API outputs, such as task statuses and media URLs. 1. Ingestion points: Output from the happyhorse_get_task tool. 2. Boundary markers: None defined in the skill body. 3. Capability inventory: Network-based tool operations for video generation and polling. 4. Sanitization: Not explicitly mentioned in the instructions.
Audit Metadata