carousell-sg

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

• Third-party content exposure detected (low risk: 0.10). The agent searches and reads public listings on Carousell via search queries and API calls, retrieving third-party user-generated listing titles and descriptions (classified as low risk because the agent actively searches/fetches specific listing content rather than monitoring an unprompted feed).

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill configures a remote Model Context Protocol (MCP) server at https://unbrowse.ai/mcp/carousell.sg and interacts with unbrowse.ai APIs at runtime, which constitute third-party/unofficial operational dependencies under the Unbrowse brand, resulting in a medium severity rating.