mfds-food-safety

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries government food safety search endpoints and public registries via a proxy, where fetched search results and database entries may contain untrusted third-party product or company descriptions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs installation and execution via npx -y @nomadamas/k-skill@0 from an unverified personal GitHub repository (NomaDamas/k-skill), constituting an unknown/weak operational dependency.