bunjang-search

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads product listings, search results, and chat messages from the Bunjang marketplace via bunjang-cli, where outsider sellers can submit arbitrary text in item descriptions, titles, and chat threads.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs runtime execution of npx -y @nomadamas/k-skill@0 via npm registry, representing an unofficial third-party operational dependency.