zipcode-search

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

• Third-party content exposure detected (low risk: 0.10). The agent queries the public ePost address search website with user-provided address keywords, ingesting external HTML response data into the LLM context.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill queries the official ePost search service over HTTPS and executes instructions retrieved via npx from @nomadamas/k-skill, establishing an unofficial external dependency with weak/unknown provenance.