mfds-drug-safety

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

• Third-party content exposure detected (low risk: 0.10). The skill queries official MFDS public drug APIs and guidelines via a proxy, where drug names or symptoms are supplied by the user during the conversation or active search, with no unmonitored outsider-authored feeds or submission queues.

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 an external CLI tool via npx from an unverified third-party npm package (@nomadamas/k-skill), which constitutes an unverified runtime external dependency.