suzuri-api
Warn
Audited by Snyk on May 11, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call and consume public SUZURI API endpoints (e.g., GET https://suzuri.jp/api/v1/products, /materials, /users) which return user-generated/untrusted product, material and profile data that the agent is expected to read and use to drive display and follow-up actions (search, create, delete, navigate), enabling indirect prompt-injection via those third-party contents.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata