brightdata-local-search

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

• Third-party content exposure detected (low risk: 0.10). The agent performs active web searches via Bright Data SERP API, ingesting fetched web pages whose content is selected by the agent's search queries.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs cloning an external repository (https://github.com/yaronbeen/unfancy-search.git) which serves as the local server runtime and pipeline dependency; however, GitHub repositories cloned by the user during setup are classified as common/reputable unofficial operational dependencies resulting in a medium risk tier.