olive-young-search

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (low risk: 0.10). The workflow queries public retail store, product, and inventory APIs via an upstream CLI, which processes untrusted external API responses containing product descriptions and store names.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to execute untrusted third-party code via npx (@nomadamas/k-skill and daiso) and clone/build an arbitrary upstream repository from GitHub (hmmhmmhm/daiso-mcp), constituting a weak/unknown/suspicious operational dependency.