suzuri-api
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of user-generated content from the SUZURI platform, which could potentially contain malicious prompt instructions.\n
- Ingestion points: The agent is instructed to fetch data from various SUZURI API endpoints, including product details, material lists, and search results (SKILL.md, references/api-reference.md).\n
- Boundary markers: There are no instructions defining boundaries between untrusted API data and the agent's core instructions.\n
- Capability inventory: The skill documents capabilities to perform network-based write operations, such as creating materials, updating text-based goods, and managing collections (SKILL.md).\n
- Sanitization: No validation or filtering mechanisms are described for data retrieved from the SUZURI API before processing by the agent.
Audit Metadata