bunjang-search

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

• Third-party content exposure detected (medium risk: 0.30). The workflow searches and reads marketplace item listings and details from Bunjang via CLI, which involves ingesting outsider-authored descriptions and content from public users.

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 npx -y @nomadamas/k-skill@0 instruct bunjang-search at runtime, establishing a weak/unknown third-party operational dependency on GitHub-hosted and npm-distributed packages.