byted-redis

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

• Third-party content exposure detected (high risk: 0.90). The skill's client and start script explicitly fetch and run a remote MCP server from GitHub (see scripts/mcp_client.py and scripts/start_volcengine_redis_mcp.sh which call uvx --from git+https://github.com/volcengine/mcp-server.git), and the agent then reads tool lists/descriptions and runtime responses from that remote server—untrusted third-party content that can influence subsequent tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). At runtime the skill explicitly fetches and runs remote code via uvx using the URL git+https://github.com/volcengine/mcp-server.git#subdirectory=server/mcp_server_redis (seen in scripts/start_volcengine_redis_mcp.sh and scripts/mcp_client.py), so external repository content is fetched and executed as a required dependency.